fix(P20 round 2): Surgical→P14+P20 (drop P10 overclaim) + terse changelog

Cross-review round 2 (Codex) 6/10 BLOCK on two residuals:
- (b) Surgical→Hygiene(P10) still overclaimed (P10 = tree cleanliness, not diff
  scope) → remap to Dep-Chain(P14) bounds-the-surface + Cross-Review(P20) flags-
  tangential-edits; drop P10 from the row.
- (d) CHANGELOG still advocacy copy → tightened to terse release-note prose
  (dropped 'widely-recognized', star count; rationale reduced to one cf. line).
+ aligned residual 'enforcing'→'backing' wording (changelog bullet, flow doc).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: Carlos D. Escobar-Valbuena

CHANGELOG.md

@@ -4,13 +4,13 @@
 
 ### feat: scaffold a Development Philosophy section into AGENTS.md/CLAUDE.md on install (BRO-1406)
 
-Every newly-bootstrapped workspace now inherits an explicit **Development Philosophy** — four guiding principles, each backed by the primitive(s) that hold it — so downstream development follows the philosophy by default, alongside the user's own project conventions. Previously the scaffold deployed the primitive contract (the *mechanism*) without its stated *intent*.
+`bstack bootstrap` now scaffolds a **Development Philosophy** section into a new workspace's `AGENTS.md` (full section) and `CLAUDE.md` (anchor). It states four guiding principles — Think Before Coding · Simplicity First · Surgical Changes · Goal-Driven Execution — and backs each with the primitive(s) that hold it: Think→P14+P15, Simplicity→P20, Surgical→P14+P20, Goal-Driven→P11+P19. A note records that enforcement strength varies (P14/P15 are hard predicates; P20 is a judgment gate) — both beat prose because the agent never grades itself.
 
-The four principles (Think Before Coding · Simplicity First · Surgical Changes · Goal-Driven Execution) are widely-recognized engineering disciplines, articulated sharply in Andrej Karpathy's observations on LLM-coding pitfalls; the most-starred public CLAUDE.md, `multica-ai/andrej-karpathy-skills` (~168k★), applies the same four. bstack's contribution is the **Ritual-vs-Substance** rule: a principle that lives only as prose decays into ritual, so each is backed by a primitive — Think→Dep-Chain (P14)+Snapshot (P15); Simplicity→Cross-Review (P20); Surgical→Hygiene (P10)+Cross-Review (P20); Goal-Driven→Empirical (P11)+Orchestrate (P19). Enforcement strength varies (P14/P15 are hard predicates; P20 is an independent-judgment gate) — both beat prose because the agent never grades itself.
+Rationale: the scaffold previously deployed the primitive contract without its stated intent. The four principles follow Andrej Karpathy's observations on LLM-coding pitfalls (cf. `multica-ai/andrej-karpathy-skills`).
 
 ### Changed
 
-- **`assets/templates/AGENTS.md.template`** — new `## Development Philosophy` section between Self-Meta Definition and the primitives table (so the *why* frames the *how*): 4-principle → enforcing-primitive table, the binding Ritual-vs-Substance rule, and an explicit invitation to extend it with project-specific principles.
+- **`assets/templates/AGENTS.md.template`** — new `## Development Philosophy` section between Self-Meta Definition and the primitives table (so the *why* frames the *how*): 4-principle → backing-primitive table, the binding Ritual-vs-Substance rule, and an explicit invitation to extend it with project-specific principles.
 - **`assets/templates/CLAUDE.md.template`** — short philosophy anchor after Identity, linking to `AGENTS.md#development-philosophy`.
 - **`references/new-workspace-flow.md`** — deployed-files table note updated to describe the philosophy section.
 

assets/templates/AGENTS.md.template

@@ -14,7 +14,7 @@ Before the twenty primitives below — which are the *mechanism* — these four
 |---|---|---|---|
 | **1. Think before coding** | Surface assumptions and trade-offs *before* writing. Trace what the change depends on and what depends on it. Ask only for what you genuinely cannot derive from the repo. | Hidden assumptions — confidently building the wrong thing. | **Dep-Chain (P14)** + **Snapshot (P15)** |
 | **2. Simplicity first** | Deliver the minimal change that solves the actual problem. No speculative features, no premature abstraction, no scope creep. | Overcomplication — code nobody asked for, harder to maintain than the problem warranted. | **Cross-Review (P20)** anti-slop gate |
-| **3. Surgical changes** | Change only what the task requires. Match the surrounding style. Don't refactor tangentially or reformat untouched lines. | Unintended edits — diffs that touch more than they should, hiding the real change and breaking unrelated things. | **Hygiene (P10)** (keeps the diff an isolated, reviewable unit) + **Cross-Review (P20)** (flags scope creep) |
+| **3. Surgical changes** | Change only what the task requires. Match the surrounding style. Don't refactor tangentially or reformat untouched lines. | Unintended edits — diffs that touch more than they should, hiding the real change and breaking unrelated things. | **Dep-Chain (P14)** (enumerating what's touched bounds the change surface) + **Cross-Review (P20)** (flags tangential edits / scope creep) |
 | **4. Goal-driven execution** | Define measurable success criteria up front, then loop — building and *verifying by interaction* — until they are met. | No verifiable "done" — work that *looks* complete without evidence it works. | **Empirical (P11)** (interaction evidence for "done") + **Orchestrate (P19)** (the verify-until-met loop) |
 
 **Enforcement strength varies by principle, and that is the point.** P14/P15 are *hard predicates* — a checker reads the response for a dependency enumeration / state snapshot. P20 is an *independent-judgment* gate that blocks a merge below threshold. Both beat prose, because in neither case is the agent the one grading itself — but only the first kind is a literal yes/no predicate. The goal is to push each principle as far down the gradient toward a hard predicate as it will go.

references/new-workspace-flow.md

@@ -17,7 +17,7 @@ Both paths wire the RCS control loop. `bootstrap.sh` scaffolds governance files
 
 | Path | Source | Purpose |
 |---|---|---|
-| `CLAUDE.md`, `AGENTS.md`, `.control/policy.yaml`, `METALAYER.md` | `assets/templates/*.template` | Governance substrate (Development Philosophy section, P-row primitives table, reflexive trigger rules, gate config). The philosophy section states the four guiding principles (think-before-coding · simplicity-first · surgical-changes · goal-driven) and binds each to its enforcing primitive, so downstream development inherits the *intent* behind the primitives — and the user can extend it with project-specific principles. |
+| `CLAUDE.md`, `AGENTS.md`, `.control/policy.yaml`, `METALAYER.md` | `assets/templates/*.template` | Governance substrate (Development Philosophy section, P-row primitives table, reflexive trigger rules, gate config). The philosophy section states the four guiding principles (think-before-coding · simplicity-first · surgical-changes · goal-driven) and backs each with the primitive(s) that hold it, so downstream development inherits the *intent* behind the primitives — and the user can extend it with project-specific principles. |
 | `.control/arcs.yaml` | `arcs.yaml.template` | Closure-contract arcs — the workspace's own editable loop definitions (5-tuple). Scaffolded by `bootstrap.sh` Phase 2 |
 | `.githooks/pre-commit` | `githook-pre-commit-l3-rate.sh.template` | G1 — blocks `git commit` over τ_a₃ L3 commit rate (bypassable with `--no-verify`) |
 | `.github/workflows/l3-stability.yml` | `gh-workflow-l3-stability.yml.template` | G2 — runs `compute-lambda` + `l3-rate-gate` on every PR touching L3 paths; comments verdict |