Skip to content

Research SPDD + Fowler Fragments + cc-connect; promote 2 rules - #7

Merged
tomqwu merged 1 commit into
mainfrom
claude/research-spdd-and-cc-connect
Jun 10, 2026
Merged

tomqwu merged 1 commit into
mainfrom
claude/research-spdd-and-cc-connect

Conversation

@tomqwu

@tomqwu tomqwu commented May 15, 2026

Copy link
Copy Markdown
Owner

Summary

Continues the research-handling pipeline for three sources: the Thoughtworks Structured-Prompt-Driven Development (SPDD) article, Martin Fowler's 29 Apr 2026 Fragments, and chenhg5/cc-connect.

  • Logged all three in docs/source-repos.md and docs/research-log.md (SPDD + Fragments promoted; cc-connect extracted).
  • Promoted two generic rules into AGENTS.md and its Copilot mirror:
    • Spec/prompt and code kept in two-way sync — behavior changes update the spec first; pure refactors update code first then sync the spec back (SPDD).
    • "Verified" means checked by a deterministic sensor (tests, types, lint, CI gate), not just read at agent throughput (Fowler/Böckeler/Parsons).
  • Added two knowledge notes (descriptive, not rules):
    • docs/knowledge/structured-prompt-driven-development.md — the seven-part REASONS Canvas, the sync flows, fitness assessment.
    • docs/knowledge/agent-integration-patterns.md — bridge-daemon, capability-interface-over-identity-switch, plugin self-registration, versioned preset-manifest patterns from cc-connect; also records cc-connect's duplicated-AGENTS.md/CLAUDE.md as a cautionary counter-example.
  • Strategy doc gains a short pointer to the SPDD note.

cc-connect stayed extracted (its generic lessons went to a knowledge note + cautionary anti-pattern; no new instruction-file rule).

Test plan

  • CI doc-quality: Tier 1 (≤200 lines, Boundaries present), Tier 2 (markdownlint), Tier 3 (lychee offline), Tier 4 (typos) all green. Tiers 1–2 verified locally via ./scripts/check.sh.
  • Confirm both new knowledge notes end with ## Boundaries and are listed in docs/knowledge/README.md.
  • Confirm AGENTS.md ↔ .github/copilot-instructions.md mirror stays in sync for the two promoted rules.
  • Spot-check every quote against the source text.

Follow-ups

  • If Tier 3/4 flag anything (proper nouns, links), autofix on this branch.
  • openspdd-style per-step CLI and provider-keyed multi-agent config left as pending observations until a runtime exists.

https://claude.ai/code/session_01AmmEaVLpyeJz7TZ3iyXtWK


Generated by Claude Code

Summary:
- Logged Thoughtworks SPDD, Fowler's 29 Apr Fragments, and chenhg5/cc-connect as sources.
- Promoted spec/code two-way sync and sensor-based verification into AGENTS.md + Copilot mirror.
- Added two knowledge notes (SPDD / REASONS Canvas; agent-integration patterns).

Changed files:
- docs/source-repos.md: 3 rows (SPDD + Fragments promoted; cc-connect extracted).
- docs/research-log.md: 3 dated observation blocks, extends/contradicts, promoted-rule rows, pending + anti-pattern entries.
- AGENTS.md: spec/code sync bullet (House style) + sensor-verification check (Validation).
- .github/copilot-instructions.md: mirrored both rules.
- docs/knowledge/structured-prompt-driven-development.md: new descriptive note.
- docs/knowledge/agent-integration-patterns.md: new descriptive note.
- docs/knowledge/README.md: listed both new notes.
- docs/ai-agent-coding-strategy.md: pointer to the SPDD note.

Validation:
- ./scripts/check.sh: Tier 1 (length, Boundaries) and Tier 2 (markdownlint) clean.
- Tier 3/4 binaries absent locally; will verify in CI.
- All new files end with a Boundaries section; all under 200 lines.

Follow-ups:
- Confirm Tier 3 (lychee) and Tier 4 (typos) pass in CI; fix if flagged.
- cc-connect left as extracted (knowledge note only, no instruction-file rule).

https://claude.ai/code/session_01AmmEaVLpyeJz7TZ3iyXtWK
@tomqwu
tomqwu marked this pull request as ready for review June 10, 2026 15:26
@tomqwu
tomqwu merged commit 4d8ec6d into main Jun 10, 2026
4 checks passed
tomqwu added a commit that referenced this pull request Jun 10, 2026
Codifies the operating policy this session has been running under: builder agents may merge after the review gate passes (CI green + LGTM marker matching head SHA + no newer blocking feedback), replacing the previous "do not merge unless the user explicitly asks" rule.

- AGENTS.md: adds the builder and reviewer prompt snippets, with explicit head-SHA tying.
- CLAUDE.md: same builder/reviewer split with a pointer to the knowledge note for scheduler, lock, and state guardrails.
- .github/copilot-instructions.md: mirrors the head-SHA approval gate for the Copilot baseline.
- docs/knowledge/agentic-pr-review-loop.md: updates the prompts, the validation checklist, and the "let the builder bypass review" framing.

Rebased onto current main (post #7 and #8); doc-quality CI passes on the rebased head.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants