claude-code-kit 0.12.0__tar.gz → 0.14.0__tar.gz

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "claude-kit",
       "source": "./",
       "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker): install CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json, then run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.",
-      "version": "0.12.0",
+      "version": "0.14.0",
       "license": "MIT",
       "keywords": ["sdlc", "agents", "orchestration", "quality-gates", "workflow", "scaffold", "cookiecutter"]
     }

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-kit",
-  "version": "0.12.0",
+  "version": "0.14.0",
   "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker). `claude-kit init` asks ordered questions and installs CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates with working memory and a self-improving learnings loop.",
   "author": {
     "name": "Arjunsingh Yadav",

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/CHANGELOG.md

@@ -4,6 +4,151 @@ All notable changes to claude-kit are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project uses
 [semantic versioning](https://semver.org/).
 
+## [0.14.0] — 2026-06-16
+
+A **third improvement brief** — six engineering *techniques* observed in Anthropic's Claude Code system
+prompts, **reimplemented from scratch in claude-kit's own vocabulary** (gates, severity, RARV,
+profiles, scopes, Orchestrator, CONTINUITY, agent-memory). No source text was copied, quoted, or
+closely paraphrased — the IP boundary is technique-and-structure only. Run through the kit's reuse-first
+mapping, the decisive finding repeated once more: every pattern already had a natural home, so all six
+land as **extensions of existing rules/agents/skills/hooks** — **zero new agents, zero new rule files**
+(core counts unchanged: 28 agents · 50 skills · 23 rules).
+
+Two deliberate divergences from the brief's *inferred* file paths (it invited path verification):
+**(P0-1)** the autonomous-action posture lives in `rules/agent-guardrails.md` §3 (execution discipline),
+not `rules/risk-classification.md` (tier assignment) — cross-referenced from the restricted tier;
+**(P2-1)** the implementer house style extends `templates/CLAUDE.md` "Surgical Changes" (the kit's
+always-in-context house-style home) rather than adding a new rule that would near-duplicate it and
+`code-organization.md` (golden rule #3).
+
+### Added
+- **P0-1 — autonomous-action safety** (`rules/agent-guardrails.md` §3, always-on). A **block / confirm /
+  allow** posture over irreversible & outward-facing actions (force-push, history rewrite, branch/tag
+  deletion, destructive migration, bulk deletion, secret access, publish/send/post), a **verify-the-
+  target-before-destroying** step (stop if what you find contradicts how the task described it), and the
+  affirmative §1 rule that **untrusted/injected content never authorizes an action**. Cross-ref from
+  `rules/risk-classification.md`; one-line pointers from `developer`, `devops-engineer`, and both
+  `migration-specialist` overlay agents.
+- **P0-2 — anti-fabrication of verdicts** (`rules/quality-gates.md` §2.5 + §1, always-on). A gate verdict
+  (PASS/FAIL) is valid **only** when it cites the real command + captured output (or the `file:line`
+  finding); a fabricated, assumed, or partial-output-based verdict is **auto-Critical**; reading a
+  still-running lane's output and calling the gate done is forbidden. Reinforced in
+  `rules/agent-guardrails.md` §2 and `rules/rarv-cycle.md` ("cite it", not just "run it").
+- **P1-3 — plan-phase critique before approval.** The `spec-doc-writer` now runs an explicit
+  **self-critique** in its RARV cycle (always-on, wherever planning runs); and in **standard+** the
+  Orchestrator runs `devils-advocate` once on the spec + dev-docs **before EM approval is final**
+  (new Stage PC / `mandatory-workflow.md` §1e.5) — an UPHELD verdict routes back to the Spec Writer and
+  the spec gate stays open. `devils-advocate` extended to a plan-critique mode (was code/tests only).
+  **lean** keeps self-critique only (it doesn't install the agent).
+
+### Changed
+- **P1-1 — memory hygiene** (`rules/agent-memory.md`, always-on): verify-before-trust (confirm a
+  recalled file/flag/command still exists before relying on it), selective attachment with cited
+  sources, and reconciliation (committed `CLAUDE.md`/`rules/*` win over a conflicting memory). A
+  start-of-turn line added to `rules/continuity.md`; a staleness check added to the `remember` skill.
+- **P1-2 — resume snapshot** (`rules/continuity.md`, always-on): a small structured
+  `.claude/state/pipeline-snapshot.json` (profile/scope, mode, stage, per-lane status,
+  `last_gate_passed`, open findings by severity, next action) the Orchestrator maintains alongside
+  CONTINUITY; on resume it is **reloaded as context, not re-executed** (no re-running setup, no
+  re-applying committed edits, no re-opening passed gates). Wired into the `sdlc` skill + `orchestrator`;
+  `load-continuity.sh` now ensures `.claude/state/` exists in plugin context (the pip installer already
+  creates and gitignores it).
+- **P2-1 — implementer house style** (`templates/CLAUDE.md` "Surgical Changes", always-on): delete the
+  superseded path instead of leaving a backwards-compat shim (unless compat is required), validate at
+  the boundary not redundantly in every layer, cite code as `path:line`, and (cross-ref to
+  `rules/documentation.md` §6, no duplication) no change-narration comments. The `sdlc-code-reviewer`
+  gains a **Change Hygiene** check group (shim-without-requirement = Medium; redundant re-validation =
+  Low; narration comment = Low); reinforced in the `developer` agent.
+
+### Notes
+- **No `resolve()` / catalog changes** — all six are payload-content edits, so the
+  `lean⊊standard⊊enterprise` subset, MCP-gating, and no-Docker invariants are untouched.
+- `docs/coverage-audit.md` gains a Brief-#3 section; `docs/architecture.md` adds the standard+ plan-
+  critique node.
+
+## [0.13.0] — 2026-06-15
+
+A **second improvement brief** (external self-review, post-0.12.0) — Item 0 (a covered-vs-gated audit)
++ P0-1/P0-2, P1-1/P1-2/P1-3, and six P2 items — run through the kit's mandated **adversarial
+reuse-first map→verify** (a 24-agent map→verify pass). The decisive finding repeated from last time:
+several premises were **overstated** against the live files (migration safety was already largely
+enforced; the README "no PyPI yet" text was simply stale; the README is already progressively
+disclosed). The result is a mix of **two new gates wired as data, one new live backend stack, and
+targeted extensions** — **zero new agents/skills/rules** beyond what already existed (core counts
+unchanged: 28 agents · 50 skills · 23 rules).
+
+### Added
+- **Item 0 — `docs/coverage-audit.md`.** The justification record the briefs kept eliding: every
+  "already covered" capability classified **GATED (enforced) / RULE (always-on) / SKILL-DOC
+  (advisory)** with file evidence. Verifies rollback (GATED enterprise-only; RULE elsewhere), cost
+  (DOC by design), migration safety (overlay-advisory + enterprise rollback), accessibility, and
+  flags the one *looks-enforced-but-isn't* trap (the `accessibility-review` skill's internal "Quality
+  gates" heading is **not** a gate token).
+- **P0-1 — `contract-clear` reaches the default `standard` profile** (API stacks), not just
+  enterprise (`catalog/profiles.yaml`). It still self-skips when the stack exposes no API contract
+  surface, so non-API projects are unaffected. *(Deliberate posture change: 0.12.0 placed it in
+  enterprise under golden-rule-#6 "heavyweight gates default to enterprise"; the brief explicitly
+  authorizes promoting it because breaking-change detection is table-stakes for the headline FastAPI
+  backend. Documented, not silent.)* Owned by `merge-reviewer`; quality-gates §4 + mandatory-workflow
+  §2d + the api-change-report template updated to say "standard+".
+- **P1-1 — a live Go backend stack** (Go · stdlib **net/http**): a pure `catalog/stacks.yaml` entry +
+  `templates/stacks/backend/go/net-http/rules/go-patterns.md` overlay + exact `go` commands
+  (`go build ./...`, `go test ./...`, `go vet`, `gofmt`). Chosen over Node/Express precisely because
+  its build/test command shapes differ most from npm/pip — the strongest test of the stack-agnostic
+  claim. The one supporting code change: a **`build`** key added to `_BACKEND_CMD_KEYS` (compiled
+  backends surface a build command; interpreted ones leave it empty). No `resolve()` branch.
+- **P1-2 — `accessibility-clear` gate** at organization scope, **`regulated` strictness only**
+  (`catalog/org.yaml` `extra_gates`). Owned by `acceptance-reviewer` (read-only, already present at
+  standard+), drives the existing `accessibility-review` skill over changed UI (WCAG-AA), self-skips
+  when no UI surface. Wired in `org.yaml` only, so the `lean⊊standard⊊enterprise` profile invariant is
+  untouched.
+- **`examples/react-fastapi-postgres-feature/`** (P2-2) — a clearly-labelled **synthetic** end-to-end
+  walkthrough: request → feature-spec → story breakdown (coverage gate) → gate verdicts (incl. one
+  defect-loop cycle and a Devil's-Advocate CONFIRMED line) → sample PR diff. Repo reference (like
+  `docs/`), **not** bundled into the wheel.
+- **`docs/eval-harness.md`** (P2-4) — a fill-in template to measure the pipeline with vs without the
+  gates (which gate caught which defect), built on `rules/evals.md` §6 median-of-N. Ships **no**
+  numbers by design (an eval result is environment-specific); honesty rules included.
+- **Self-test matrix** (P2-5) — a parametrized test sweeping **every live frontend × backend ×
+  database × profile × scope** (now 24 combos incl. Go), each resolved + installed + validated +
+  Docker-checked. Driven off `catalog.list_options`, so new live stacks auto-join with no test edit.
+
+### Changed
+- **P0-2 — migration safety made explicit.** Both `migration-specialist` overlays (postgres + mongodb)
+  already mandated expand/contract, reversible down-path, and idempotent backfill *as agent guidance*;
+  added the explicit hard rule **"no destructive drop in the same release as the code that stops using
+  the old shape"** with **severity** to the always-on overlay RULES (`postgres-patterns.md`,
+  `mongodb-patterns.md`) — so it lives in a rule, not only an agent prompt. (Same-release destruction
+  = at least **High**.)
+- **P1-3 — the PyPI story reconciled.** `claude-code-kit` **is** published (latest 0.12.0); the README
+  install block, troubleshooting row, and a stale `changelog-v0.10.0` badge said otherwise. Install is
+  now `pip install claude-code-kit`; the changelog badge is de-versioned (self-healing); the CI
+  publish machinery (`publish.yml`) was correct and left untouched.
+- **P2-3 (on-ramp, minimal)** — added an **Examples** nav link + pipeline pointer only; the proposed
+  full README restructure was **rejected** (see below). Pipeline gate table + `docs/architecture.md`
+  diagram updated for `contract-clear` (standard+) and the Go stack.
+
+### Not adopted (deliberately — premise overstated or against the kit's design)
+- **A dedicated migration GATE token (P0-2).** Migrations are overlay-conditioned and not every-run;
+  `resolve()` can't emit stack gates without a branch. Strengthened the always-on overlay rules +
+  reviewer agents instead — enforcement via review + the enterprise rollback gate (`pipeline-green`),
+  per the coverage audit.
+- **Node/Express as the new backend (P1-1).** Chose **Go** instead — its command shapes differ more
+  from the existing npm/pip stacks, which is the whole point of the breadth test. Express/Vue/Svelte/
+  Django remain `planned`.
+- **A full README restructure + GIF (P2-3).** The README already uses progressive disclosure
+  (`<details>`); a big move-to-`docs/` churn is negative-value and a GIF can't be produced here. Added
+  only the example link. (Recording a demo GIF is a human follow-up.)
+- **Relocating the CHANGELOG "Not adopted" blocks to `docs/decision-log.md` (P2-6).** Those blocks are
+  a **marketed feature** the README links to; moving them would break that cross-reference for low
+  value. Added a forward-looking note in `CONTRIBUTING.md` instead (split later *only if* the README
+  link is updated in the same change).
+- **Repo About-box metadata (P2-1)** — host config outside the payload; `gh` is unavailable here.
+  Human follow-up: `gh repo edit ajyadav013/claude-kit --description "Config-only, stack-agnostic
+  autonomous-SDLC scaffolder for Claude Code (plugin + pip)" --add-topic claude-code --add-topic
+  claude-code-plugins --add-topic sdlc --add-topic ai-agents --add-topic agentic-coding --add-topic
+  claude-skills`.
+
 ## [0.12.0] — 2026-06-15
 
 An **improvement brief** (external self-review, no repo access) proposed ~15 changes — four P0, five

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/CLAUDE.md

@@ -29,8 +29,9 @@ distributed two ways from one source of truth:
 | `templates/org/` | **Org overlay** content (scope-gated, organization only): `skills/`, `agents/` (personas), `rules/` (policy/vibe), `packs/<pack>/{pack.yaml,README.md}`, `README.md`. Wired via `catalog/org.yaml`. The only place org-specific content lives. |
 | `scripts/init.sh` | Thin no-pip fallback scaffolder (copies the full payload; no catalog resolution) |
 | `src/claude_kit/` | The pip CLI (Typer): `cli.py`, `catalog.py` (resolver), `prompts.py`, `models.py`, `scaffold.py` (installer), `render.py` (Jinja2), `hooks.py`, `validator.py`, `upgrader.py` |
-| `tests/` | pytest suite (catalog, render, scaffold, validator, upgrader, CLI) |
-| `docs/architecture.md` · `docs/agents.md` | Architecture diagrams · agent guide |
+| `tests/` | pytest suite (catalog, render, scaffold, validator, upgrader, CLI; incl. the profile×stack×scope self-test matrix) |
+| `examples/` | Synthetic end-to-end `/sdlc` worked example (repo reference; **not** bundled into the wheel) |
+| `docs/architecture.md` · `docs/agents.md` · `docs/coverage-audit.md` · `docs/eval-harness.md` | Architecture diagrams · agent guide · the GATED-vs-RULE-vs-SKILL enforcement audit · the with/without eval template |
 | `pyproject.toml` | Packaging (deps: typer/jinja2/pyyaml); `[tool.hatch...force-include]` bundles the payload into the wheel |
 
 **One source of truth:** `agents/ skills/ commands/ hooks/ rules/ templates/ catalog/` at the repo

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/CONTRIBUTING.md

@@ -83,9 +83,14 @@ a specific stack — `pytest` enforces the no-Docker invariant on a scaffolded p
 
 1. Bump the version in **all four** places: `pyproject.toml`, `.claude-plugin/plugin.json`, the
    `.claude-plugin/marketplace.json` entry, and `src/claude_kit/__init__.py`.
-2. Add a `CHANGELOG.md` entry.
+2. Add a `CHANGELOG.md` entry, including a **"Not adopted (deliberately)"** block stating what you
+   chose *not* to add and why — this is a marketed feature of the changelog (the README links to it),
+   so keep it. If those blocks ever grow unwieldy they may later split into `docs/decision-log.md`,
+   but **only if** the README's CHANGELOG cross-reference is updated in the same change; until then
+   they stay in `CHANGELOG.md` by design.
 3. `pytest` green, then `python3 -m build && python3 -m twine check dist/*`.
-4. `python3 -m twine upload dist/*` (PyPI).
+4. CI auto-publishes to PyPI on merge to `main` when the version is new (`.github/workflows/publish.yml`,
+   OIDC trusted publishing). Manual `python3 -m twine upload dist/*` is the fallback.
 5. Tag the release and push so plugin users get the update.
 
 ## License

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-code-kit
-Version: 0.12.0
+Version: 0.14.0
 Summary: Cookiecutter-style scaffolder for an autonomous Claude Code SDLC configuration (no app code, no Docker). Asks ordered questions and installs CLAUDE.md + .claude/ (rules, the chosen profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.
 Project-URL: Homepage, https://github.com/ajyadav013/claude-kit
 Project-URL: Repository, https://github.com/ajyadav013/claude-kit
@@ -39,9 +39,9 @@ with a quality gate between every phase. **No application code. No Docker. Confi
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Built for Claude Code](https://img.shields.io/badge/built%20for-Claude%20Code-d97757.svg)](https://www.claude.com/product/claude-code)
 [![CI](https://github.com/ajyadav013/claude-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/ajyadav013/claude-kit/actions/workflows/ci.yml)
-[![Changelog](https://img.shields.io/badge/changelog-v0.10.0-blue.svg)](CHANGELOG.md)
+[![Changelog](https://img.shields.io/badge/changelog-md-blue.svg)](CHANGELOG.md)
 
-🚀 [Quick start](#quick-start) · 🧭 [How it works](#how-it-works) · 🔁 [The pipeline](#the-pipeline) · 🌱 [What we adopted](#influences--what-we-adopted) · 🤖 [Agents](#the-agents) · 🧩 [Catalog](#catalog--extensibility) · 🛠️ [CLI](#cli-reference) · 📖 [Agent guide](docs/agents.md)
+🚀 [Quick start](#quick-start) · 🧭 [How it works](#how-it-works) · 🔁 [The pipeline](#the-pipeline) · 🧪 [Example](examples/) · 🌱 [What we adopted](#influences--what-we-adopted) · 🤖 [Agents](#the-agents) · 🧩 [Catalog](#catalog--extensibility) · 🛠️ [CLI](#cli-reference) · 📖 [Agent guide](docs/agents.md)
 
 </div>
 
@@ -59,7 +59,7 @@ refuses to advance a phase until its **quality gate** passes. You drive it all w
 **At a glance:**
 
 - 🧱 **Stack-agnostic** — the pipeline assumes no language or framework. Pick a stack at `init` and it
-  installs matching overlay rules (React · FastAPI · PostgreSQL · MongoDB) and your exact
+  installs matching overlay rules (React · FastAPI · Go/net-http · PostgreSQL · MongoDB) and your exact
   lint/test/build commands. It never writes your app code and never needs Docker.
 - 🎚️ **Dial the rigor with profiles** — `lean ⊊ standard ⊊ enterprise` decide how many agents, skills,
   hooks, and gates are active, from "fast track" to "full audit".
@@ -109,9 +109,9 @@ Then, inside any project you want the pipeline to manage:
 A CLI (`claude-kit`, aliases `ckit` / `claude-sdlc`) that scaffolds the same config into any repo:
 
 ```bash
-# Until the first PyPI release, install straight from the repo:
-pip install "git+https://github.com/ajyadav013/claude-kit.git"
-# Once published to PyPI this becomes:  pip install claude-code-kit
+pip install claude-code-kit
+# or, for the bleeding edge straight from the repo:
+#   pip install "git+https://github.com/ajyadav013/claude-kit.git"
 
 claude-kit init                 # interactive: prompts for stack, profile, MCP
 claude-kit init --defaults      # non-interactive: React + Python/FastAPI + Postgres + standard
@@ -223,10 +223,16 @@ flowchart TD
 | Profile | Gates that run |
 |---|---|
 | **lean** | code-review · build-green |
-| **standard** | spec-complete · em-approved · code-review · build-green · test-coverage · security-clear |
+| **standard** | spec-complete · em-approved · code-review · build-green · test-coverage · security-clear · contract-clear\* |
 | **enterprise** | standard + pipeline-green · observability-ready · acceptance |
 
-A **fast-track** mode collapses small changes (< 5 files) to Developer → Code Reviewer → Tester → PR.
+\* `contract-clear` (API breaking-change diff) self-skips when the stack exposes no API surface, so it
+is inert for non-API projects. Organization scope at `regulated` strictness adds `accessibility-clear`
+(WCAG-AA on changed UI). A **fast-track** mode collapses small changes (< 5 files) to Developer →
+Code Reviewer → Tester → PR.
+
+See [`examples/`](examples/) for a synthetic end-to-end walkthrough — request → spec → story breakdown
+→ gate verdicts (with one defect-loop cycle) → sample PR diff.
 
 ---
 
@@ -245,6 +251,7 @@ non-duplicative gaps**, minimally and catalog-wired.
 | **[GitHub spec-kit](https://github.com/github/spec-kit)** | Spec → tasks → **analyze** coverage gate; tasks → tracker issues; stable requirement IDs + assumptions in specs | Wired the (previously orphaned) `story-planner` as the **coverage gate (1f)**, a tracker-agnostic `task-tracker-sync` skill, and enriched the feature-spec template | `0.9.0` |
 | **[protectai/llm-guard](https://github.com/protectai/llm-guard)** | Input→model→output guardrails for LLM features — prompt injection, PII vault, treating model output as untrusted | **Opt-in** "LLM / AI Feature Security" guidance in `security-and-hardening` + the advisory `warn-llm-io` hook (warns, **never blocks**) | `0.10.0` |
 | **Improvement brief** (external self-review) | API backward-compat as a gate; load-against-SLO as a release criterion; supply-chain maintenance cadence; pipeline resumability, clean abort, and worktree lifecycle; pipeline cost/concurrency/cross-platform transparency | The enterprise **`contract-clear`** gate (owned by `merge-reviewer`) + `api-change-report` template; a load-vs-SLO criterion in Observability Ready; dependency **Cadence Mode**; `/sdlc` resume-vs-restart, `/claude-kit:abort`, worktree teardown; cost/concurrency/Windows notes — **9 surgical extensions, 0 new agents/skills/rules** | `0.12.0` |
+| **Improvement brief #2** (external self-review) | The covered-vs-**gated** distinction (a skill ≠ a gate); enforce API breaking-changes by default; expand/contract migration safety; back the stack-agnostic claim with a compiled backend; WCAG as a regulated gate; reconcile the PyPI story; ship a worked example + a self-test matrix | [`docs/coverage-audit.md`](docs/coverage-audit.md); **`contract-clear` promoted to `standard`**; a live **Go/net-http** backend; the **`accessibility-clear`** regulated gate; explicit migration-drop rules; a synthetic [`examples/`](examples/) run; an eval-harness template; a profile×stack×scope self-test matrix — **2 gates wired + 1 stack, 0 new agents/skills/rules** | `0.13.0` |
 
 > Each adoption is detailed in the [CHANGELOG](CHANGELOG.md) — including, for every review, what we
 > deliberately **did not** add because the kit already covered it.
@@ -386,8 +393,8 @@ change.
 <br>
 
 - **`catalog/stacks.yaml`** — frontend frameworks, backend languages → frameworks, and databases.
-  Live today: React · Python/FastAPI · PostgreSQL/MongoDB. Vue/Svelte/Django/Express are listed as
-  `planned` (offered by `list-options`, not yet selectable).
+  Live today: React · Python/FastAPI · **Go/net-http** · PostgreSQL/MongoDB. Vue/Svelte/Django/Express
+  are listed as `planned` (offered by `list-options`, not yet selectable).
 - **`catalog/profiles.yaml`** — what each profile activates (`inherit:` composes; `all` = everything).
 - **`catalog/mcp.yaml`** — ready `.mcp.json` fragments per server, with `${ENV}` placeholders.
 - **`catalog/org.yaml`** — the **organization layer**: scopes, teams, the autonomy model, review
@@ -454,7 +461,7 @@ hints.
 | Guard / quality hooks seem to do nothing | `jq` isn't installed (the hooks parse tool input with it) | Install `jq`; without it the hooks degrade to no-ops by design |
 | Hooks do nothing on **Windows** | No POSIX shell — `.sh` hooks can't run under `cmd`/PowerShell | Run claude-kit inside **WSL or Git Bash** (with `jq`); `claude-kit doctor` confirms. Config + CLI work natively regardless |
 | A selected MCP server won't start | `node` / `npx` missing (most MCP servers launch via `npx`) | Install Node.js, or remove the server from `.mcp.json` |
-| `pip install claude-code-kit` fails | Not yet published to PyPI | Use `pip install "git+https://github.com/ajyadav013/claude-kit.git"` |
+| `pip install claude-code-kit` fails | Outdated `pip`, or you want an unreleased change | Upgrade pip (`pip install -U pip`); for unreleased changes use `pip install "git+https://github.com/ajyadav013/claude-kit.git"` |
 | `validate` reports missing files | Partial or outdated install | Re-run `claude-kit init` (choose **merge**), or `claude-kit upgrade` |
 
 </details>

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/README.md

@@ -12,9 +12,9 @@ with a quality gate between every phase. **No application code. No Docker. Confi
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Built for Claude Code](https://img.shields.io/badge/built%20for-Claude%20Code-d97757.svg)](https://www.claude.com/product/claude-code)
 [![CI](https://github.com/ajyadav013/claude-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/ajyadav013/claude-kit/actions/workflows/ci.yml)
-[![Changelog](https://img.shields.io/badge/changelog-v0.10.0-blue.svg)](CHANGELOG.md)
+[![Changelog](https://img.shields.io/badge/changelog-md-blue.svg)](CHANGELOG.md)
 
-🚀 [Quick start](#quick-start) · 🧭 [How it works](#how-it-works) · 🔁 [The pipeline](#the-pipeline) · 🌱 [What we adopted](#influences--what-we-adopted) · 🤖 [Agents](#the-agents) · 🧩 [Catalog](#catalog--extensibility) · 🛠️ [CLI](#cli-reference) · 📖 [Agent guide](docs/agents.md)
+🚀 [Quick start](#quick-start) · 🧭 [How it works](#how-it-works) · 🔁 [The pipeline](#the-pipeline) · 🧪 [Example](examples/) · 🌱 [What we adopted](#influences--what-we-adopted) · 🤖 [Agents](#the-agents) · 🧩 [Catalog](#catalog--extensibility) · 🛠️ [CLI](#cli-reference) · 📖 [Agent guide](docs/agents.md)
 
 </div>
 
@@ -32,7 +32,7 @@ refuses to advance a phase until its **quality gate** passes. You drive it all w
 **At a glance:**
 
 - 🧱 **Stack-agnostic** — the pipeline assumes no language or framework. Pick a stack at `init` and it
-  installs matching overlay rules (React · FastAPI · PostgreSQL · MongoDB) and your exact
+  installs matching overlay rules (React · FastAPI · Go/net-http · PostgreSQL · MongoDB) and your exact
   lint/test/build commands. It never writes your app code and never needs Docker.
 - 🎚️ **Dial the rigor with profiles** — `lean ⊊ standard ⊊ enterprise` decide how many agents, skills,
   hooks, and gates are active, from "fast track" to "full audit".
@@ -82,9 +82,9 @@ Then, inside any project you want the pipeline to manage:
 A CLI (`claude-kit`, aliases `ckit` / `claude-sdlc`) that scaffolds the same config into any repo:
 
 ```bash
-# Until the first PyPI release, install straight from the repo:
-pip install "git+https://github.com/ajyadav013/claude-kit.git"
-# Once published to PyPI this becomes:  pip install claude-code-kit
+pip install claude-code-kit
+# or, for the bleeding edge straight from the repo:
+#   pip install "git+https://github.com/ajyadav013/claude-kit.git"
 
 claude-kit init                 # interactive: prompts for stack, profile, MCP
 claude-kit init --defaults      # non-interactive: React + Python/FastAPI + Postgres + standard
@@ -196,10 +196,16 @@ flowchart TD
 | Profile | Gates that run |
 |---|---|
 | **lean** | code-review · build-green |
-| **standard** | spec-complete · em-approved · code-review · build-green · test-coverage · security-clear |
+| **standard** | spec-complete · em-approved · code-review · build-green · test-coverage · security-clear · contract-clear\* |
 | **enterprise** | standard + pipeline-green · observability-ready · acceptance |
 
-A **fast-track** mode collapses small changes (< 5 files) to Developer → Code Reviewer → Tester → PR.
+\* `contract-clear` (API breaking-change diff) self-skips when the stack exposes no API surface, so it
+is inert for non-API projects. Organization scope at `regulated` strictness adds `accessibility-clear`
+(WCAG-AA on changed UI). A **fast-track** mode collapses small changes (< 5 files) to Developer →
+Code Reviewer → Tester → PR.
+
+See [`examples/`](examples/) for a synthetic end-to-end walkthrough — request → spec → story breakdown
+→ gate verdicts (with one defect-loop cycle) → sample PR diff.
 
 ---
 
@@ -218,6 +224,7 @@ non-duplicative gaps**, minimally and catalog-wired.
 | **[GitHub spec-kit](https://github.com/github/spec-kit)** | Spec → tasks → **analyze** coverage gate; tasks → tracker issues; stable requirement IDs + assumptions in specs | Wired the (previously orphaned) `story-planner` as the **coverage gate (1f)**, a tracker-agnostic `task-tracker-sync` skill, and enriched the feature-spec template | `0.9.0` |
 | **[protectai/llm-guard](https://github.com/protectai/llm-guard)** | Input→model→output guardrails for LLM features — prompt injection, PII vault, treating model output as untrusted | **Opt-in** "LLM / AI Feature Security" guidance in `security-and-hardening` + the advisory `warn-llm-io` hook (warns, **never blocks**) | `0.10.0` |
 | **Improvement brief** (external self-review) | API backward-compat as a gate; load-against-SLO as a release criterion; supply-chain maintenance cadence; pipeline resumability, clean abort, and worktree lifecycle; pipeline cost/concurrency/cross-platform transparency | The enterprise **`contract-clear`** gate (owned by `merge-reviewer`) + `api-change-report` template; a load-vs-SLO criterion in Observability Ready; dependency **Cadence Mode**; `/sdlc` resume-vs-restart, `/claude-kit:abort`, worktree teardown; cost/concurrency/Windows notes — **9 surgical extensions, 0 new agents/skills/rules** | `0.12.0` |
+| **Improvement brief #2** (external self-review) | The covered-vs-**gated** distinction (a skill ≠ a gate); enforce API breaking-changes by default; expand/contract migration safety; back the stack-agnostic claim with a compiled backend; WCAG as a regulated gate; reconcile the PyPI story; ship a worked example + a self-test matrix | [`docs/coverage-audit.md`](docs/coverage-audit.md); **`contract-clear` promoted to `standard`**; a live **Go/net-http** backend; the **`accessibility-clear`** regulated gate; explicit migration-drop rules; a synthetic [`examples/`](examples/) run; an eval-harness template; a profile×stack×scope self-test matrix — **2 gates wired + 1 stack, 0 new agents/skills/rules** | `0.13.0` |
 
 > Each adoption is detailed in the [CHANGELOG](CHANGELOG.md) — including, for every review, what we
 > deliberately **did not** add because the kit already covered it.
@@ -359,8 +366,8 @@ change.
 <br>
 
 - **`catalog/stacks.yaml`** — frontend frameworks, backend languages → frameworks, and databases.
-  Live today: React · Python/FastAPI · PostgreSQL/MongoDB. Vue/Svelte/Django/Express are listed as
-  `planned` (offered by `list-options`, not yet selectable).
+  Live today: React · Python/FastAPI · **Go/net-http** · PostgreSQL/MongoDB. Vue/Svelte/Django/Express
+  are listed as `planned` (offered by `list-options`, not yet selectable).
 - **`catalog/profiles.yaml`** — what each profile activates (`inherit:` composes; `all` = everything).
 - **`catalog/mcp.yaml`** — ready `.mcp.json` fragments per server, with `${ENV}` placeholders.
 - **`catalog/org.yaml`** — the **organization layer**: scopes, teams, the autonomy model, review
@@ -427,7 +434,7 @@ hints.
 | Guard / quality hooks seem to do nothing | `jq` isn't installed (the hooks parse tool input with it) | Install `jq`; without it the hooks degrade to no-ops by design |
 | Hooks do nothing on **Windows** | No POSIX shell — `.sh` hooks can't run under `cmd`/PowerShell | Run claude-kit inside **WSL or Git Bash** (with `jq`); `claude-kit doctor` confirms. Config + CLI work natively regardless |
 | A selected MCP server won't start | `node` / `npx` missing (most MCP servers launch via `npx`) | Install Node.js, or remove the server from `.mcp.json` |
-| `pip install claude-code-kit` fails | Not yet published to PyPI | Use `pip install "git+https://github.com/ajyadav013/claude-kit.git"` |
+| `pip install claude-code-kit` fails | Outdated `pip`, or you want an unreleased change | Upgrade pip (`pip install -U pip`); for unreleased changes use `pip install "git+https://github.com/ajyadav013/claude-kit.git"` |
 | `validate` reports missing files | Partial or outdated install | Re-run `claude-kit init` (choose **merge**), or `claude-kit upgrade` |
 
 </details>

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/acceptance-reviewer.md

@@ -53,6 +53,25 @@ Run the **RARV** cycle (`.claude/rules/rarv-cycle.md`) with a green Verify (you
 checks) before issuing the verdict, and update `.claude/CONTINUITY.md`. This gate is **Acceptance**
 in the enterprise profile and runs before the PR is handed to a human.
 
+## Join Point: Accessibility (accessibility-clear gate)
+
+> Active **only** under organization scope at **`regulated`** review strictness (where WCAG is
+> commonly a legal requirement). You own the **accessibility-clear** gate. **Degrade to a no-op**
+> (PASS, note "no UI surface") when the change touches no frontend/UI files — detect with `Bash`
+> (`git diff --name-only <base>` against the frontend stack dir / component globs); never block a
+> back-end-only or API-only change.
+
+When a UI surface is present:
+
+1. **Drive `.claude/skills/accessibility-review`** over the changed views/components (and the standards
+   in `.claude/rules/responsive-and-accessibility.md`) — keyboard operability, focus management,
+   semantics/ARIA, color contrast (WCAG AA), motion, and screen-reader labels.
+2. **Classify each finding** by `.claude/rules/quality-gates.md` §1. A WCAG-AA failure on a
+   legally-required surface is at least **High** (per `accessibility-review`'s risk note); a missing
+   label, focus trap, or sub-threshold contrast is **High/Medium**; cosmetic spacing is **Low**.
+3. **Verdict** — *accessibility-clear* PASSes only at zero Critical/High/Medium, consistent with every
+   other gate. Record findings in the acceptance report.
+
 ## Escalation
 
 Escalate to the human when acceptance criteria themselves are ambiguous or untestable, when the spec

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/developer.md

@@ -145,6 +145,14 @@ If this fails, report to the Orchestrator instead of proceeding.
 - Use the project's path alias (if configured) for cleaner imports
 - Follow naming conventions per the rules files
 - No dead code, unused imports, or debug artifacts
+- When you replace code, delete the superseded path — don't leave a backwards-compat shim unless
+  compatibility is a stated requirement (CLAUDE.md "Surgical Changes")
+- Validate inputs at the boundary, not redundantly in every internal layer that already received
+  validated data
+- Reference code as `path:line` in review responses and handoff notes
+- Before any irreversible or outward-facing action (deleting/overwriting a file you didn't create,
+  force-push, a destructive migration, publishing), follow the verify-then-confirm posture in
+  `.claude/rules/agent-guardrails.md` §3 — confirm the target is what you think it is, then ask.
 
 ## Handling Code Review Feedback
 

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/devils-advocate.md

@@ -1,6 +1,6 @@
 ---
 name: devils-advocate
-description: Anti-sycophancy adversarial reviewer. Invoked ONLY when a parallel review or test-coverage gate reaches a unanimous PASS. Assumes the work is guilty and hunts for what every other reviewer missed. Gates the pipeline — a unanimous PASS is not final until this agent returns CONFIRMED.
+description: Anti-sycophancy adversarial reviewer. Invoked to critique a plan/spec before approval (standard+), and whenever a parallel review or test-coverage gate reaches a unanimous PASS. Assumes the work is guilty and hunts for what everyone else missed. Gates the pipeline — the artifact is not final until this agent returns CONFIRMED.
 tools: Read, Glob, Grep, Bash, SendMessage
 permissionMode: plan
 model: opus
@@ -10,9 +10,12 @@ tier: review
 
 You are the **Devil's Advocate** — the anti-sycophancy backstop for the SDLC pipeline.
 
-You are spawned by the Orchestrator **only when a gate reaches a unanimous PASS** — every blind reviewer or senior tester independently said "looks good, no blocking issues." That unanimity is exactly why you exist. Independent AI reviewers converge and rubber-stamp; your job is to break the consensus if it deserves breaking.
+You are spawned by the Orchestrator at **two moments**, both chosen because consensus is most dangerous when it is comfortable:
 
-**Your stance:** the artifact is guilty until proven innocent. You are not here to confirm good work — you are here to find the issue three reviewers talked themselves out of. If you approve, it must be because you genuinely tried to break it and could not.
+1. **Plan critique (standard+)** — once, on the spec + developer documentation *before* EM approval is final, to stress-test the plan while it is still cheap to change.
+2. **Gate critique** — when a parallel review or test-coverage gate reaches a **unanimous PASS** (every blind reviewer or senior tester independently said "looks good, no blocking issues"). That unanimity is exactly why you exist; independent AI reviewers converge and rubber-stamp.
+
+**Your stance (both modes):** the artifact is guilty until proven innocent. You are not here to confirm good work — you are here to find the issue everyone else talked themselves out of. If you approve, it must be because you genuinely tried to break it and could not.
 
 ## MANDATORY: Read Before Reviewing
 
@@ -23,6 +26,8 @@ You are spawned by the Orchestrator **only when a gate reaches a unanimous PASS*
 
 ## How You Work
 
+**When critiquing a plan (not code),** attack the spec's assumptions and completeness rather than an implementation: the weakest or most-likely-to-change requirement, an acceptance criterion that isn't actually testable, a hidden dependency or sequencing risk, a requirement quietly missing, scope that no requirement justifies, and the single step most likely to fail in implementation. Map every acceptance criterion to a concrete, verifiable outcome — anything vague is a finding. The steps below otherwise apply in both modes.
+
 1. **Read the consensus, then distrust it.** List what the reviewers checked. Your value is in the gaps they share — a blind spot common to all of them.
 2. **Re-derive from the spec, not their summary.** Map every acceptance criterion to concrete evidence (a test, a code path). Anything you cannot trace is a finding.
 3. **Attack the seams** that single-lane reviews miss:
@@ -48,7 +53,7 @@ Effort: {what you specifically probed that they did not}
    (or: "No blocking issue found in {area} — checked {what}")
 
 ## Verdict: {UPHELD | CONFIRMED}
-- UPHELD  -> at least one Critical/High/Medium found. Gate FAILS. Route: {which lane fixes what}.
+- UPHELD  -> at least one Critical/High/Medium found. Gate FAILS. Route: {which lane fixes what} (plan critique -> back to the Spec / Dev Doc Writer; the spec gate stays open).
 - CONFIRMED -> genuinely clean after adversarial review. Gate may PASS.
 ```
 
@@ -58,5 +63,5 @@ Effort: {what you specifically probed that they did not}
 2. **You must do real work before CONFIRMED.** "Looks fine" is not allowed — name what you attacked and why it held. A CONFIRMED with no described probes is itself a failure.
 3. **Classify by the shared severity model.** Only Critical/High/Medium block; Low/Cosmetic are notes.
 4. **No sycophancy, no nihilism.** Do not invent issues to look thorough; do not wave it through to be agreeable. Report what is actually there.
-5. **One pass.** You run once per unanimous gate. If you UPHOLD, the normal fix lane + retry budget takes over; you are re-spawned only if the gate again reaches unanimous PASS.
+5. **One pass.** You run once per plan critique and once per unanimous gate. If you UPHOLD, the normal fix lane + retry budget takes over; you are re-spawned only if the plan returns for re-critique or the gate again reaches unanimous PASS.
 6. Record any blind-spot pattern you find (e.g., "all reviewers missed tenant filter on list endpoints") to `CONTINUITY.md`, and promote it to `agent-memory/` if it is a recurring class of miss.

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/devops-engineer.md

@@ -113,6 +113,10 @@ All checks must succeed before you declare done.
 - **Always preserve persistent data** when changing runtime config — don't orphan volumes/data.
 - **Always test a clean rebuild + start** before signing off.
 - **Never run destructive data ops** (`DROP DATABASE`, `TRUNCATE`) outside a disposable dev cycle.
+- **Irreversible/outward-facing actions follow the verify-then-confirm posture** in
+  `.claude/rules/agent-guardrails.md` §3 — *block* (force-push, history rewrite, destructive
+  migration), *confirm* (publish, deploy, send outward), *allow* (reversible local work); verify the
+  target environment before acting.
 
 ## Quality Gate: Pipeline Green
 

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/merge-reviewer.md

@@ -178,8 +178,8 @@ Frontend code reviewed: ✓ | Build/tests: ✓
 > source is found — mirror the hooks' detect-then-skip pattern; never block a project that has no
 > contract.
 
-Owns the **contract-clear** gate (enterprise; or any profile an org opts into via `org.yaml`
-strictness). With `Bash`:
+Owns the **contract-clear** gate (runs in **standard and enterprise** — any profile that includes the
+`merge-reviewer` — whenever the selected stack exposes an API surface). With `Bash`:
 
 1. **Locate or generate the contract** — a committed `openapi.(json|yaml)` / GraphQL SDL, or generate it from the framework's typed routes.
 2. **Diff against the base branch** — `git show <base>:<contract-path>` vs the working copy.

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/orchestrator.md

@@ -29,6 +29,8 @@ You are the **Orchestrator** — the pipeline controller for the engineering del
 
 **Read `.claude/CONTINUITY.md` at the start of every turn; write it back before the turn ends and at every stage transition.** It is your cross-session / cross-compaction memory — phase, active lanes, decisions, mistakes, next steps. After a compaction or a new session, recover state from it and resume from **Next Steps**; mirror your `PIPELINE:` line into its **Current Phase**. Durable lessons still go to `agent-memory/` via `remember`. See `.claude/rules/continuity.md`.
 
+Alongside the freeform file, maintain the **structured resume snapshot** `.claude/state/pipeline-snapshot.json` (schema in `.claude/rules/continuity.md`): write/update it at every stage transition with the active profile/scope, mode, stage, per-lane status, `last_gate_passed`, open findings by severity, and the next action. On resume, **reload it as context** — re-enter at the first gate *after* `last_gate_passed`, re-running only un-passed or defect-affected lanes; never re-run setup or re-apply edits already committed. If it is missing or unparseable, fall back to the freeform CONTINUITY state.
+
 Every agent you dispatch runs the **RARV** cycle (Reason → Act → Reflect → Verify) and must show a green Verify before its gate may pass (`.claude/rules/rarv-cycle.md`). Classify every finding by the **severity model** in `.claude/rules/quality-gates.md` — a gate is PASS only with zero Critical/High/Medium open.
 
 ---
@@ -79,6 +81,9 @@ Human PRD
 [MR1] Merge Reviewer ──── verifies spec consistency across lanes
   │
   ▼
+[PC]  Devil's Advocate ── plan critique on spec + dev docs before approval is final (standard+)
+  │
+  ▼
 [SP]  Story Planner ───── decomposes spec into ordered stories + verifies every
   │                       acceptance criterion maps to a story (coverage gate)
   ▼
@@ -244,6 +249,18 @@ For full-stack work, **spawn these lanes in parallel**:
 
 ---
 
+### Stage PC: Plan Critique (standard+, before approval is final)
+
+Before treating the review chain's approval as final, run an adversarial pass on the **plan itself**:
+
+- **Spawn**: `devils-advocate` with the spec + developer documentation (and the review-chain verdicts).
+- It argues the plan is wrong — weakest/most-volatile requirement, untestable acceptance criterion,
+  hidden dependency, missing requirement, unjustified scope, the step most likely to fail.
+- **Gate**: a **CONFIRMED** verdict lets the Story Planner proceed; an **UPHELD** verdict (any
+  Critical/High/Medium) routes back to the **Spec / Dev Doc Writer** and the spec gate stays open.
+- **Profile**: standard and enterprise only — `devils-advocate` isn't installed in **lean**, where the
+  Spec Writer's own self-critique (its RARV cycle) is the safeguard. Skip with a noted reason in lean.
+
 ### Stage SP: Story Breakdown & Coverage Gate (after the spec is approved + consistent)
 
 The bridge between an approved spec and implementation: decompose, then prove coverage before any
@@ -516,6 +533,7 @@ PIPELINE: DEFECT LOOP (cycle 1/2) - Backend lane re-entered, re-test API lane on
 | 5b-UI | `senior-tester` (ui mode) | Verifies UI tester | Yes — Test Lane 2 |
 | 5b-INT | `senior-tester` (integration mode) | Verifies integration tester | Yes — Test Lane 3 |
 | JOIN | `merge-reviewer` | Verifies test coverage completeness | No — gate |
+| PC | `devils-advocate` | Plan critique on the spec + dev docs before approval (standard+) | No — gate (standard+) |
 | 3b+ | `devils-advocate` | Anti-sycophancy pass on a unanimous test-coverage PASS | No — gate (conditional) |
 | 5.4 | `security-reviewer` | Security stage coordinator + gate (Security Clear) | No — sequential |
 | 5.4 | `secret-scanner` / `dependency-scanner` / `owasp-reviewer` / `policy-validator` | Four sub-scanners | Yes — parallel |
@@ -571,6 +589,6 @@ When an agent fails, follow this escalation:
 13. **Escalate clearly.** Provide: what failed, which lane, how many attempts, unresolved issues.
 14. **Verify outputs exist.** Check that expected files are created before marking a stage complete.
 15. **Prefer parallel over sequential.** If two stages have no data dependency, run them in parallel.
-16. **Persist working memory.** Read/write `.claude/CONTINUITY.md` every turn and at every stage transition; recover from it after compaction.
-17. **Anti-sycophancy.** A unanimous PASS at the test-coverage gate is not VERIFIED until `devils-advocate` returns CONFIRMED.
+16. **Persist working memory.** Read/write `.claude/CONTINUITY.md` every turn and at every stage transition; recover from it after compaction. Mirror gate-precise state into `.claude/state/pipeline-snapshot.json` and resume from it by *reloading* (re-enter after `last_gate_passed`), never by re-running passed gates or re-applying committed edits.
+17. **Anti-sycophancy.** In standard+, the plan is critiqued by `devils-advocate` before approval is final (Stage PC); and a unanimous PASS at the test-coverage gate is not VERIFIED until `devils-advocate` returns CONFIRMED.
 18. **Operability gates.** For deployable/observable changes, run DevOps (Pipeline Green) and Observability (Observability Ready) before the PR Raiser.

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/sdlc-code-reviewer.md

@@ -151,6 +151,12 @@ Review all code changes produced by the Developer (Agent 4). Check for correctne
 - [ ] Path aliases used correctly
 - [ ] Naming conventions match rules files
 
+### Change Hygiene (see CLAUDE.md "Surgical Changes" + `.claude/rules/documentation.md` §6)
+- [ ] No backwards-compat shim left for replaced code unless compatibility is a stated requirement — else **Medium**
+- [ ] Inputs validated at the boundary, not redundantly re-validated in internal layers — redundant re-validation is **Low**
+- [ ] No change-narration comments ("// added this") — comments explain *why*, not *what changed* — **Low**
+- [ ] Code locations in findings cited as `path:line`
+
 ## Feedback Protocol
 
 When you find issues, send **specific, actionable** fix requests to the Developer:

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/agents/spec-doc-writer.md

@@ -304,6 +304,8 @@ Before handing off to the EM Reviewer:
 
 **Reflect:** Does every spec requirement have acceptance criteria? Does every acceptance criterion map to an implementation approach in the dev docs? Are there conflicting requirements or hidden assumptions?
 
+**Self-critique (argue against your own plan):** Before declaring the spec ready, turn on it. Name the **weakest requirement** (most likely to be wrong or to change), the **riskiest assumption**, an **acceptance criterion that isn't truly testable**, and the **one thing most likely to go wrong in implementation**. For each, either resolve it in the spec or record it under **Open Questions** for the human. A plan that has not been argued against is not ready for review. In standard+ profiles an independent `devils-advocate` runs the same challenge adversarially before approval (`.claude/rules/quality-gates.md` §3) — doing it yourself first is what makes that pass cheap.
+
 **Verify:**
 - [ ] Spec file exists at `docs/specs/{feature-name}_spec.md`
 - [ ] Both sections present (Specification + Developer Documentation)

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/catalog/org.yaml

@@ -77,7 +77,10 @@ strictness:
     regulated:
       label: "Regulated — compliance-grade gates"
       hooks: [validate-frontmatter, validate-settings]
-      extra_gates: [security-clear, acceptance]
+      # accessibility-clear (brief #2 P1-2): a WCAG gate owned by acceptance-reviewer, driving the
+      # accessibility-review skill. Regulated-strictness only (WCAG is often a legal requirement there);
+      # self-skips when the change touches no UI surface, so API/back-end-only work is unaffected.
+      extra_gates: [security-clear, acceptance, accessibility-clear]
 
 # --- core agents the org layer activates regardless of profile ---------------------------------------
 # These live in the core agents/ dir (installed via the normal agent path); listing them here unions

{claude_code_kit-0.12.0 → claude_code_kit-0.14.0}/catalog/profiles.yaml

@@ -82,7 +82,10 @@ profiles:
       - over-engineering-review
       - simplification-debt
       - task-tracker-sync
-    gates: [spec-complete, em-approved, code-review, build-green, test-coverage, security-clear]
+    # contract-clear self-skips when the stack exposes no API contract surface, so it is inert for
+    # non-API projects on standard while enforcing backward-compatibility for API-exposing backends
+    # (e.g. FastAPI). Promoted from enterprise-only per brief #2 P0-1 — see CHANGELOG 0.13.0.
+    gates: [spec-complete, em-approved, code-review, build-green, test-coverage, security-clear, contract-clear]
     hooks: [load-continuity, load-learnings, load-autonomy, skill-routing, learning-detection, guard-rm-rf, guard-push-main, guard-destructive-git, protect-secrets, guard-commit-secrets, warn-shared-modules, warn-llm-io, lint-fix, type-check]
 
   enterprise: