diff --git a/.changeset/legit-docs-and-seo.md b/.changeset/legit-docs-and-seo.md
deleted file mode 100644
index 4892a46..0000000
--- a/.changeset/legit-docs-and-seo.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Project legitimacy and SEO rollout (Wave 1 of v1.0.0):
-
-- Added `CODE_OF_CONDUCT.md` (Contributor Covenant 2.1), `CONTRIBUTING.md`, `SECURITY.md` (GitHub Private Vulnerability Reporting only — no email exposure), `CHANGELOG.md`.
-- Added `.github/copilot-instructions.md` for `gh copilot review`, plus `PULL_REQUEST_TEMPLATE.md`, issue forms (`bug_report.yml`, `feature_request.yml`, `config.yml`), and `FUNDING.yml`.
-- Rewrote root `README.md` with badges row, "Why Tokenometer vs alternatives" comparison table (vs `tokencost`, `tiktoken`, `gpt-tokenizer`, `promptfoo`, `gpt-token-counter-live`), ASCII demo of CLI table output, and project-health checklist.
-- Extended npm `keywords` and `description` across `tokenometer` (CLI), `@tokenometer/core`, and `@tokenometer/action` for SEO. Root description now reads: "Tokenometer — LLM cost calculator, token counter, and CI cost-guardrail Action for Claude, GPT-4o, Gemini."
-- Added Marketplace publish prep (`.github/release-notes-v1.0.0.md`) and awesome-list PR templates (`.github/awesome-list-prs/`).
-- Initialized Changesets for auto-bump + auto-CHANGELOG-generation on release. Replaced the manual `release.yml` workflow with the Changesets-driven version-PR + publish flow.
diff --git a/.changeset/wave-2-action-per-file-diff.md b/.changeset/wave-2-action-per-file-diff.md
deleted file mode 100644
index 8add080..0000000
--- a/.changeset/wave-2-action-per-file-diff.md
+++ /dev/null
@@ -1,8 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Action sticky PR comment now includes a top-N changed-file table with per-file
-Δ tokens and Δ USD, plus a collapsible "all files" section. New optional
-`top-n-files` input controls N (default 5).
diff --git a/.changeset/wave-2-cli-wiring.md b/.changeset/wave-2-cli-wiring.md
deleted file mode 100644
index 869dda6..0000000
--- a/.changeset/wave-2-cli-wiring.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-CLI gains:
-- Auto provider detection when `--model` is omitted (picks based on which `*_API_KEY` env is set).
-- `.tokenometer.yml` config loading (walk-up); `--no-config` and `--config <path>` overrides.
-- `--by-file` per-file token/cost attribution table.
-- `--output table|json|sarif` for machine-readable output.
-- `--image <path>` (repeatable) for vision-token cost estimation across Claude / GPT-4o / Gemini.
diff --git a/.changeset/wave-2-core-additions.md b/.changeset/wave-2-core-additions.md
deleted file mode 100644
index 6f981b9..0000000
--- a/.changeset/wave-2-core-additions.md
+++ /dev/null
@@ -1,10 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Core lib additions for v1.0.0:
-
-- `loadConfig` / `parseConfig` for `.tokenometer.yml`.
-- `toSarif` SARIF 2.1.0 output.
-- Vision token estimators for Anthropic, OpenAI, and Google.
diff --git a/.changeset/wave-3-claude-code-skill.md b/.changeset/wave-3-claude-code-skill.md
deleted file mode 100644
index 75f48a6..0000000
--- a/.changeset/wave-3-claude-code-skill.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Add `@tokenometer/claude-code-skill` — a Claude Code skill that teaches
-Claude Code agents to invoke `npx tokenometer` for prompt-cost analysis.
-Install via `~/.claude/skills/tokenometer/SKILL.md`. Submission to
-community skill registry tracked separately.
diff --git a/.changeset/wave-3-latency.md b/.changeset/wave-3-latency.md
deleted file mode 100644
index 45b5aab..0000000
--- a/.changeset/wave-3-latency.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Add `--latency` flag — measures real generation latency (TTFT + total ms +
-tokens/sec, p50/p95/mean over n trials) alongside token cost. Implies
-`--empirical`. Default trials = 3, configurable via `--latency-trials <n>`
-(1-10). Bumps default `--max-spend` to $0.25 to cover the n × 200-token
-generations. Supported providers: Anthropic, OpenAI, Google, Cohere,
-Mistral (latter two are metered).
diff --git a/.changeset/wave-3-mistral-cohere.md b/.changeset/wave-3-mistral-cohere.md
deleted file mode 100644
index 2e3cbf1..0000000
--- a/.changeset/wave-3-mistral-cohere.md
+++ /dev/null
@@ -1,19 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Add Mistral and Cohere providers.
-
-- Mistral: `mistral-tokenizer-js` for SentencePiece family (Mistral 7B,
-  Mixtral, Mistral Large 2407, Codestral); `chars/4` heuristic for Tekken
-  models (NeMo, Pixtral, Mistral Small 2409+, Devstral, Mistral Medium
-  2505+, Magistral, Ministral). All marked `approximate: true`. Empirical
-  mode unsupported (Mistral has no public token-count API).
-- Cohere: offline heuristic `chars/4` (Cohere SDK is REST-only; no offline
-  tokenizer ships in JS). Empirical via `POST /v1/tokenize` when
-  `COHERE_API_KEY` is set.
-
-Pricing for Mistral auto-sourced from `@tokenlens/models/mistral`. Cohere
-pricing comes from `LOCAL_OVERRIDES` (`command-r`, `command-r-plus`)
-because `@tokenlens/models` does not yet ship a Cohere catalog at v1.3.0.
diff --git a/.changeset/wave-3-playground-showcase.md b/.changeset/wave-3-playground-showcase.md
deleted file mode 100644
index 9023fe2..0000000
--- a/.changeset/wave-3-playground-showcase.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Playground (`https://tokenometer.vercel.app`) gains showcase pages for
-every Wave 2 feature: `/diff`, `/by-file`, `/sarif`, `/vision`,
-`/config-builder`, `/init`, `/models` (Cost Atlas + per-model SEO pages),
-plus placeholder pages for the VS Code extension and Claude Code skill.
-</content>
-</invoke>
\ No newline at end of file
diff --git a/.changeset/wave-3-vscode-extension.md b/.changeset/wave-3-vscode-extension.md
deleted file mode 100644
index 76f09d9..0000000
--- a/.changeset/wave-3-vscode-extension.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Add VS Code / Cursor extension (`@tokenometer/vscode`). Status bar shows
-live token count + USD cost for the active editor file across Claude,
-GPT-4o, and Gemini. Reuses `@tokenometer/core`. Marketplace publish
-follows in Phase I.
diff --git a/.changeset/wave-4-docs-seo-sweep.md b/.changeset/wave-4-docs-seo-sweep.md
deleted file mode 100644
index a69f9c4..0000000
--- a/.changeset/wave-4-docs-seo-sweep.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Documentation + SEO sweep: README, per-package READMEs, package.json
-descriptions and keywords updated to reflect every shipped feature
-(CLI flags, GitHub Action, VS Code extension, Claude Code skill,
-Mistral + Cohere providers, latency benchmarking, vision tokens, SARIF).
-Repo metadata + awesome-list templates regenerated. No source code
-changes.
diff --git a/.changeset/wave-4-phase-i-release-pipeline.md b/.changeset/wave-4-phase-i-release-pipeline.md
deleted file mode 100644
index 67f8bcc..0000000
--- a/.changeset/wave-4-phase-i-release-pipeline.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-"tokenometer": minor
-"@tokenometer/core": minor
----
-
-Unified release pipeline (Phase I): one merge of the Version Packages PR
-publishes tokenometer + @tokenometer/core to npm with provenance, creates
-the GitHub Release (which republishes the Action to GitHub Marketplace),
-publishes the VS Code extension to VS Code Marketplace + Open VSX, runs
-a post-publish smoke test, verifies the Marketplace listing, and triggers
-the Vercel deploy hook. Local `npm run smoke` runs the full sweep (lint,
-typecheck, test, build, benchmarks, CLI smoke).
diff --git a/packages/action/package.json b/packages/action/package.json
index aa67089..d5018c6 100644
--- a/packages/action/package.json
+++ b/packages/action/package.json
@@ -30,7 +30,7 @@
     "@actions/core": "^1.11.1",
     "@actions/exec": "^1.1.1",
     "@actions/github": "^6.0.0",
-    "@tokenometer/core": "0.0.2",
+    "@tokenometer/core": "0.1.0",
     "minimatch": "^10.2.5"
   },
   "devDependencies": {
diff --git a/packages/cli/CHANGELOG.md b/packages/cli/CHANGELOG.md
new file mode 100644
index 0000000..e6c04c9
--- /dev/null
+++ b/packages/cli/CHANGELOG.md
@@ -0,0 +1,91 @@
+# tokenometer
+
+## 0.1.0
+
+### Minor Changes
+
+- [#11](https://github.com/faraa2m/tokenometer/pull/11) [`a864454`](https://github.com/faraa2m/tokenometer/commit/a8644542d65641a4d8804ec4c4153bcfb2ccbf10) Thanks [@faraa2m](https://github.com/faraa2m)! - Project legitimacy and SEO rollout (Wave 1 of v1.0.0):
+
+  - Added `CODE_OF_CONDUCT.md` (Contributor Covenant 2.1), `CONTRIBUTING.md`, `SECURITY.md` (GitHub Private Vulnerability Reporting only — no email exposure), `CHANGELOG.md`.
+  - Added `.github/copilot-instructions.md` for `gh copilot review`, plus `PULL_REQUEST_TEMPLATE.md`, issue forms (`bug_report.yml`, `feature_request.yml`, `config.yml`), and `FUNDING.yml`.
+  - Rewrote root `README.md` with badges row, "Why Tokenometer vs alternatives" comparison table (vs `tokencost`, `tiktoken`, `gpt-tokenizer`, `promptfoo`, `gpt-token-counter-live`), ASCII demo of CLI table output, and project-health checklist.
+  - Extended npm `keywords` and `description` across `tokenometer` (CLI), `@tokenometer/core`, and `@tokenometer/action` for SEO. Root description now reads: "Tokenometer — LLM cost calculator, token counter, and CI cost-guardrail Action for Claude, GPT-4o, Gemini."
+  - Added Marketplace publish prep (`.github/release-notes-v1.0.0.md`) and awesome-list PR templates (`.github/awesome-list-prs/`).
+  - Initialized Changesets for auto-bump + auto-CHANGELOG-generation on release. Replaced the manual `release.yml` workflow with the Changesets-driven version-PR + publish flow.
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - Action sticky PR comment now includes a top-N changed-file table with per-file
+  Δ tokens and Δ USD, plus a collapsible "all files" section. New optional
+  `top-n-files` input controls N (default 5).
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - CLI gains:
+
+  - Auto provider detection when `--model` is omitted (picks based on which `*_API_KEY` env is set).
+  - `.tokenometer.yml` config loading (walk-up); `--no-config` and `--config <path>` overrides.
+  - `--by-file` per-file token/cost attribution table.
+  - `--output table|json|sarif` for machine-readable output.
+  - `--image <path>` (repeatable) for vision-token cost estimation across Claude / GPT-4o / Gemini.
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - Core lib additions for v1.0.0:
+
+  - `loadConfig` / `parseConfig` for `.tokenometer.yml`.
+  - `toSarif` SARIF 2.1.0 output.
+  - Vision token estimators for Anthropic, OpenAI, and Google.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add `@tokenometer/claude-code-skill` — a Claude Code skill that teaches
+  Claude Code agents to invoke `npx tokenometer` for prompt-cost analysis.
+  Install via `~/.claude/skills/tokenometer/SKILL.md`. Submission to
+  community skill registry tracked separately.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add `--latency` flag — measures real generation latency (TTFT + total ms +
+  tokens/sec, p50/p95/mean over n trials) alongside token cost. Implies
+  `--empirical`. Default trials = 3, configurable via `--latency-trials <n>`
+  (1-10). Bumps default `--max-spend` to $0.25 to cover the n × 200-token
+  generations. Supported providers: Anthropic, OpenAI, Google, Cohere,
+  Mistral (latter two are metered).
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add Mistral and Cohere providers.
+
+  - Mistral: `mistral-tokenizer-js` for SentencePiece family (Mistral 7B,
+    Mixtral, Mistral Large 2407, Codestral); `chars/4` heuristic for Tekken
+    models (NeMo, Pixtral, Mistral Small 2409+, Devstral, Mistral Medium
+    2505+, Magistral, Ministral). All marked `approximate: true`. Empirical
+    mode unsupported (Mistral has no public token-count API).
+  - Cohere: offline heuristic `chars/4` (Cohere SDK is REST-only; no offline
+    tokenizer ships in JS). Empirical via `POST /v1/tokenize` when
+    `COHERE_API_KEY` is set.
+
+  Pricing for Mistral auto-sourced from `@tokenlens/models/mistral`. Cohere
+  pricing comes from `LOCAL_OVERRIDES` (`command-r`, `command-r-plus`)
+  because `@tokenlens/models` does not yet ship a Cohere catalog at v1.3.0.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Playground (`https://tokenometer.vercel.app`) gains showcase pages for
+  every Wave 2 feature: `/diff`, `/by-file`, `/sarif`, `/vision`,
+  `/config-builder`, `/init`, `/models` (Cost Atlas + per-model SEO pages),
+  plus placeholder pages for the VS Code extension and Claude Code skill.
+  </content>
+  </invoke>
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add VS Code / Cursor extension (`@tokenometer/vscode`). Status bar shows
+  live token count + USD cost for the active editor file across Claude,
+  GPT-4o, and Gemini. Reuses `@tokenometer/core`. Marketplace publish
+  follows in Phase I.
+
+- [#15](https://github.com/faraa2m/tokenometer/pull/15) [`3681ae3`](https://github.com/faraa2m/tokenometer/commit/3681ae35d021a22a300271e2ea945cfeaeca9a0e) Thanks [@faraa2m](https://github.com/faraa2m)! - Documentation + SEO sweep: README, per-package READMEs, package.json
+  descriptions and keywords updated to reflect every shipped feature
+  (CLI flags, GitHub Action, VS Code extension, Claude Code skill,
+  Mistral + Cohere providers, latency benchmarking, vision tokens, SARIF).
+  Repo metadata + awesome-list templates regenerated. No source code
+  changes.
+
+- [#16](https://github.com/faraa2m/tokenometer/pull/16) [`dd9dab3`](https://github.com/faraa2m/tokenometer/commit/dd9dab3e06bbaf374b72d1903055b8a22472e5a1) Thanks [@faraa2m](https://github.com/faraa2m)! - Unified release pipeline (Phase I): one merge of the Version Packages PR
+  publishes tokenometer + @tokenometer/core to npm with provenance, creates
+  the GitHub Release (which republishes the Action to GitHub Marketplace),
+  publishes the VS Code extension to VS Code Marketplace + Open VSX, runs
+  a post-publish smoke test, verifies the Marketplace listing, and triggers
+  the Vercel deploy hook. Local `npm run smoke` runs the full sweep (lint,
+  typecheck, test, build, benchmarks, CLI smoke).
+
+### Patch Changes
+
+- Updated dependencies [[`a864454`](https://github.com/faraa2m/tokenometer/commit/a8644542d65641a4d8804ec4c4153bcfb2ccbf10), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`3681ae3`](https://github.com/faraa2m/tokenometer/commit/3681ae35d021a22a300271e2ea945cfeaeca9a0e), [`dd9dab3`](https://github.com/faraa2m/tokenometer/commit/dd9dab3e06bbaf374b72d1903055b8a22472e5a1)]:
+  - @tokenometer/core@0.1.0
diff --git a/packages/cli/package.json b/packages/cli/package.json
index 9d271cd..42ce7bb 100644
--- a/packages/cli/package.json
+++ b/packages/cli/package.json
@@ -1,6 +1,6 @@
 {
   "name": "tokenometer",
-  "version": "0.0.2",
+  "version": "0.1.0",
   "description": "Tokenometer CLI — LLM token cost + latency benchmarking across Claude, GPT-4o, Gemini, Mistral, and Cohere. Multi-format, empirical mode, vision tokens, SARIF output.",
   "license": "MIT",
   "author": "Faraazuddin Mohammed <mohdfaraaz1@gmail.com>",
@@ -79,7 +79,7 @@
     "clean": "rm -rf dist"
   },
   "dependencies": {
-    "@tokenometer/core": "0.0.2",
+    "@tokenometer/core": "0.1.0",
     "image-size": "^2.0.2"
   },
   "devDependencies": {
diff --git a/packages/core/CHANGELOG.md b/packages/core/CHANGELOG.md
new file mode 100644
index 0000000..78b8d6d
--- /dev/null
+++ b/packages/core/CHANGELOG.md
@@ -0,0 +1,86 @@
+# @tokenometer/core
+
+## 0.1.0
+
+### Minor Changes
+
+- [#11](https://github.com/faraa2m/tokenometer/pull/11) [`a864454`](https://github.com/faraa2m/tokenometer/commit/a8644542d65641a4d8804ec4c4153bcfb2ccbf10) Thanks [@faraa2m](https://github.com/faraa2m)! - Project legitimacy and SEO rollout (Wave 1 of v1.0.0):
+
+  - Added `CODE_OF_CONDUCT.md` (Contributor Covenant 2.1), `CONTRIBUTING.md`, `SECURITY.md` (GitHub Private Vulnerability Reporting only — no email exposure), `CHANGELOG.md`.
+  - Added `.github/copilot-instructions.md` for `gh copilot review`, plus `PULL_REQUEST_TEMPLATE.md`, issue forms (`bug_report.yml`, `feature_request.yml`, `config.yml`), and `FUNDING.yml`.
+  - Rewrote root `README.md` with badges row, "Why Tokenometer vs alternatives" comparison table (vs `tokencost`, `tiktoken`, `gpt-tokenizer`, `promptfoo`, `gpt-token-counter-live`), ASCII demo of CLI table output, and project-health checklist.
+  - Extended npm `keywords` and `description` across `tokenometer` (CLI), `@tokenometer/core`, and `@tokenometer/action` for SEO. Root description now reads: "Tokenometer — LLM cost calculator, token counter, and CI cost-guardrail Action for Claude, GPT-4o, Gemini."
+  - Added Marketplace publish prep (`.github/release-notes-v1.0.0.md`) and awesome-list PR templates (`.github/awesome-list-prs/`).
+  - Initialized Changesets for auto-bump + auto-CHANGELOG-generation on release. Replaced the manual `release.yml` workflow with the Changesets-driven version-PR + publish flow.
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - Action sticky PR comment now includes a top-N changed-file table with per-file
+  Δ tokens and Δ USD, plus a collapsible "all files" section. New optional
+  `top-n-files` input controls N (default 5).
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - CLI gains:
+
+  - Auto provider detection when `--model` is omitted (picks based on which `*_API_KEY` env is set).
+  - `.tokenometer.yml` config loading (walk-up); `--no-config` and `--config <path>` overrides.
+  - `--by-file` per-file token/cost attribution table.
+  - `--output table|json|sarif` for machine-readable output.
+  - `--image <path>` (repeatable) for vision-token cost estimation across Claude / GPT-4o / Gemini.
+
+- [#13](https://github.com/faraa2m/tokenometer/pull/13) [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802) Thanks [@faraa2m](https://github.com/faraa2m)! - Core lib additions for v1.0.0:
+
+  - `loadConfig` / `parseConfig` for `.tokenometer.yml`.
+  - `toSarif` SARIF 2.1.0 output.
+  - Vision token estimators for Anthropic, OpenAI, and Google.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add `@tokenometer/claude-code-skill` — a Claude Code skill that teaches
+  Claude Code agents to invoke `npx tokenometer` for prompt-cost analysis.
+  Install via `~/.claude/skills/tokenometer/SKILL.md`. Submission to
+  community skill registry tracked separately.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add `--latency` flag — measures real generation latency (TTFT + total ms +
+  tokens/sec, p50/p95/mean over n trials) alongside token cost. Implies
+  `--empirical`. Default trials = 3, configurable via `--latency-trials <n>`
+  (1-10). Bumps default `--max-spend` to $0.25 to cover the n × 200-token
+  generations. Supported providers: Anthropic, OpenAI, Google, Cohere,
+  Mistral (latter two are metered).
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add Mistral and Cohere providers.
+
+  - Mistral: `mistral-tokenizer-js` for SentencePiece family (Mistral 7B,
+    Mixtral, Mistral Large 2407, Codestral); `chars/4` heuristic for Tekken
+    models (NeMo, Pixtral, Mistral Small 2409+, Devstral, Mistral Medium
+    2505+, Magistral, Ministral). All marked `approximate: true`. Empirical
+    mode unsupported (Mistral has no public token-count API).
+  - Cohere: offline heuristic `chars/4` (Cohere SDK is REST-only; no offline
+    tokenizer ships in JS). Empirical via `POST /v1/tokenize` when
+    `COHERE_API_KEY` is set.
+
+  Pricing for Mistral auto-sourced from `@tokenlens/models/mistral`. Cohere
+  pricing comes from `LOCAL_OVERRIDES` (`command-r`, `command-r-plus`)
+  because `@tokenlens/models` does not yet ship a Cohere catalog at v1.3.0.
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Playground (`https://tokenometer.vercel.app`) gains showcase pages for
+  every Wave 2 feature: `/diff`, `/by-file`, `/sarif`, `/vision`,
+  `/config-builder`, `/init`, `/models` (Cost Atlas + per-model SEO pages),
+  plus placeholder pages for the VS Code extension and Claude Code skill.
+  </content>
+  </invoke>
+
+- [#14](https://github.com/faraa2m/tokenometer/pull/14) [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587) Thanks [@faraa2m](https://github.com/faraa2m)! - Add VS Code / Cursor extension (`@tokenometer/vscode`). Status bar shows
+  live token count + USD cost for the active editor file across Claude,
+  GPT-4o, and Gemini. Reuses `@tokenometer/core`. Marketplace publish
+  follows in Phase I.
+
+- [#15](https://github.com/faraa2m/tokenometer/pull/15) [`3681ae3`](https://github.com/faraa2m/tokenometer/commit/3681ae35d021a22a300271e2ea945cfeaeca9a0e) Thanks [@faraa2m](https://github.com/faraa2m)! - Documentation + SEO sweep: README, per-package READMEs, package.json
+  descriptions and keywords updated to reflect every shipped feature
+  (CLI flags, GitHub Action, VS Code extension, Claude Code skill,
+  Mistral + Cohere providers, latency benchmarking, vision tokens, SARIF).
+  Repo metadata + awesome-list templates regenerated. No source code
+  changes.
+
+- [#16](https://github.com/faraa2m/tokenometer/pull/16) [`dd9dab3`](https://github.com/faraa2m/tokenometer/commit/dd9dab3e06bbaf374b72d1903055b8a22472e5a1) Thanks [@faraa2m](https://github.com/faraa2m)! - Unified release pipeline (Phase I): one merge of the Version Packages PR
+  publishes tokenometer + @tokenometer/core to npm with provenance, creates
+  the GitHub Release (which republishes the Action to GitHub Marketplace),
+  publishes the VS Code extension to VS Code Marketplace + Open VSX, runs
+  a post-publish smoke test, verifies the Marketplace listing, and triggers
+  the Vercel deploy hook. Local `npm run smoke` runs the full sweep (lint,
+  typecheck, test, build, benchmarks, CLI smoke).
diff --git a/packages/core/package.json b/packages/core/package.json
index 9d5c87b..aea1462 100644
--- a/packages/core/package.json
+++ b/packages/core/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@tokenometer/core",
-  "version": "0.0.2",
+  "version": "0.1.0",
   "description": "Tokenometer core library — multi-provider LLM token cost, latency, and vision-token estimation with empirical countTokens fallback (Anthropic, OpenAI, Google, Mistral, Cohere).",
   "license": "MIT",
   "author": "Faraazuddin Mohammed <mohdfaraaz1@gmail.com>",
diff --git a/packages/vscode/CHANGELOG.md b/packages/vscode/CHANGELOG.md
index 2057992..c8720a9 100644
--- a/packages/vscode/CHANGELOG.md
+++ b/packages/vscode/CHANGELOG.md
@@ -1,5 +1,12 @@
 # Changelog
 
+## 0.0.3
+
+### Patch Changes
+
+- Updated dependencies [[`a864454`](https://github.com/faraa2m/tokenometer/commit/a8644542d65641a4d8804ec4c4153bcfb2ccbf10), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`cc745d5`](https://github.com/faraa2m/tokenometer/commit/cc745d5701bec2e9fd4f52afd008b87e63f06802), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`061e0c5`](https://github.com/faraa2m/tokenometer/commit/061e0c577fce3ecc09c6a201a408cd1a360d5587), [`3681ae3`](https://github.com/faraa2m/tokenometer/commit/3681ae35d021a22a300271e2ea945cfeaeca9a0e), [`dd9dab3`](https://github.com/faraa2m/tokenometer/commit/dd9dab3e06bbaf374b72d1903055b8a22472e5a1)]:
+  - @tokenometer/core@0.1.0
+
 ## Unreleased
 
 - Initial scaffold. Status bar shows live token count and USD cost for the
diff --git a/packages/vscode/package.json b/packages/vscode/package.json
index 6a6d97a..24dc137 100644
--- a/packages/vscode/package.json
+++ b/packages/vscode/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@tokenometer/vscode",
-  "version": "0.0.2",
+  "version": "0.0.3",
   "displayName": "Tokenometer",
   "description": "Tokenometer for VS Code / Cursor — live token count and USD cost in the status bar for LLM prompts (Claude, GPT-4o, Gemini, Mistral, Cohere).",
   "publisher": "faraa2m",
@@ -105,7 +105,7 @@
     "package:vsix": "npm run build && vsce package --no-dependencies"
   },
   "dependencies": {
-    "@tokenometer/core": "0.0.2"
+    "@tokenometer/core": "0.1.0"
   },
   "devDependencies": {
     "@biomejs/biome": "^1.9.4",
diff --git a/packages/web/package.json b/packages/web/package.json
index 46757f8..91be376 100644
--- a/packages/web/package.json
+++ b/packages/web/package.json
@@ -13,7 +13,7 @@
   "dependencies": {
     "@anthropic-ai/sdk": "^0.40.0",
     "@google/generative-ai": "^0.21.0",
-    "@tokenometer/core": "0.0.2",
+    "@tokenometer/core": "0.1.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-router-dom": "^7.15.0"