CLAUDE.md

1# story: e38s08
2# story: e51s05
3# story: e45s22
4# story: e45s23
5# story: e55s03
6 
7# bigpowers — Claude Code
8 
9Read CONVENTIONS.md before any GitHub or git operation.
10 
11[`constitution.md`](constitution.md) is a consolidated entry point synthesizing
12this project's doctrine (this file, CONVENTIONS.md, docs/PRINCIPLES.md,
13docs/references/*.md) into bigspec's B0-B10 + Capstone blocks, with citations
14back to the fuller text. It's a starting point for a reader, not a
15replacement — this file remains fully authoritative for its own content today.
16 
17<!-- BEGIN bigpowers:context-routing -->
18## Context Routing
19 
20Load subdirectory context **by file glob** — do not read the full doc tree up front.
21 
22| Glob / trigger | Load first | Fallback |
23|----------------|------------|----------|
24| `skills/**` | Active skill's `SKILL.md` + sibling `REFERENCE.md` if linked | `SKILL-INDEX.md` |
25| `specs/epics/**` | Capsule `epic.yaml` + active story `-tasks.yaml` | `specs/release-plan.yaml` |
26| `specs/product/**` | `SCOPE_LATEST.yaml`, `VISION_LATEST.yaml` | `specs/README.md` |
27| `specs/tech-architecture/**` | `tech-stack.md` + epic `eNN-TEST_PLAN_LATEST.md` if present | `CONVENTIONS.md` |
28| `scripts/**` | `CONVENTIONS.md` § Generated artifact targets | This file § Commands |
29| `website/**` | `website/README.md` if present | Never edit `website/src/content/docs/` (generated) |
30| `docs/**` | Matching doc under `docs/` | `docs/references/` |
31| Default / session start | This file → `CONVENTIONS.md` → `specs/state.yaml` | `survey-context` |
32 
33Sub-AGENTS.md files (when present in consumer projects) override this table for their directory only.
34<!-- END bigpowers:context-routing -->
35 
36<!-- BEGIN bigpowers:learned-preferences -->
37## Learned User Preferences
38 
39_Durable preferences discovered across sessions. Update via `session-state` — do not infer from chat alone._
40 
41- Prefer `rtk`-prefixed shell commands for git, test, and build output (token savings).
42- Run Preflight before forward work; never dismiss red gates as pre-existing.
43- Edit `skills/*/SKILL.md` sources only — never `.cursor/rules/` or `.gemini/` artifacts.
44 
45## Workspace Facts
46 
47_Stable repo facts — prefer these over re-discovery._
48 
49- Stack: Markdown / Bash documentation project; skills sync via `bash scripts/sync-skills.sh`.
50- Planning SoT: `specs/state.yaml`, `specs/release-plan.yaml`, `specs/execution-status.yaml`.
51- Story traceability: `# story: eNNsNN` tags in implementing files; `bash scripts/trace-stories.sh --strict` in CI.
52- Rule matrix: `bash scripts/compile-rule-matrix.sh` → `specs/rule-matrix.json` (P0–P3 tiers from CONVENTIONS.md).
53<!-- END bigpowers:learned-preferences -->
54 
55## Project
56 
57bigpowers — agent skills for spec-driven, test-first software development by solo developers (skill count and catalog are auto-generated in `SKILL-INDEX.md`; never hardcode the count in docs).
58Stack: Markdown / Bash (documentation-based; skills integrate with Claude Code, Cursor, Gemini CLI)
59 
60## Commands
61 
62| Action  | Command |
63|---------|---------|
64| Install | `npm install -g bigpowers && bigpowers setup` |
65| Run     | `bash scripts/sync-skills.sh` |
66| Test    | N/A (documentation project) |
67| Build   | `bash scripts/install.sh` (from source) |
68| Lint    | `bash scripts/sync-skills.sh` (validates SKILL.md syntax) |
69| Validate specs YAML | `bash scripts/validate-specs-yaml.sh` |
70| Typecheck | N/A (Markdown / Bash project) |
71| CI platform | GitHub Actions (`.github/workflows/publish.yml`, `sync-skills.yml`, `golden-suite.yml`) |
72| Compliance | `npm run compliance` |
73| Verification Gates | `bash scripts/run-verification-gates.sh` |
74| Traceability | `bash scripts/trace-stories.sh --strict` | grep for story tags (traceability check) |
75| Preflight | `npm run compliance && bash scripts/run-verification-gates.sh && bash scripts/sync-skills.sh && bash scripts/trace-stories.sh --strict` | Full local green stack before forward work. Chain ends on `--strict` traceability — no trailing always-exit-0 step. |
76| Catalog drift (advisory) | `bash scripts/check-catalog-drift.sh` | e54s02 Confirm gate during catalog freeze — always exits 0; run manually when changing skills, not part of Preflight. |
77| CI | `gh pr checks` | Remote CI green when a PR is open |
78 
79### Pre-Merge Checklist
80 
81Before opening a PR or landing a branch, run:
82 
83```bash
84npm run compliance && bash scripts/run-verification-gates.sh
85```
86 
87If any gate fails, fix before merging. Run `--baseline` after any intentional increase in skill count or structure.
88 
89**BCP Plus:** For stories sized with the 13-dimension BCP Plus methodology, confirm the `bcp_plus_breakdown` is present in the epic YAML and carried into `state.yaml` as `epic_cycle.bcp_plus`. See `docs/references/bcp-plus.md` for the NFR Gate pattern.
90 
91## Architecture
92 
93Collection of verb-noun skills under `skills/`, each with a SKILL.md source file and supporting documentation. Runtime specs live in `specs/state.yaml`, `specs/release-plan.yaml`, and `specs/execution-status.yaml`; intent in `specs/product/`; epic shards in `specs/epics/`. The sync-skills.sh script auto-generates artifacts for Cursor (.cursor/rules) and Gemini CLI (.gemini/extensions/bigpowers/) from SKILL.md sources. All planning output goes to specs/ at the project root.
94 
95## Conventions
96 
97- Skill directories under `skills/` use verb-noun naming (two words, kebab-case)
98- Every skill has a single SKILL.md file as its source of truth
99- All planning/spec output goes to specs/ at project root
100- Artifacts in .cursor/rules and .gemini/ are auto-generated; edit SKILL.md, not artifacts
101- Run sync-skills.sh after any SKILL.md changes to regenerate artifacts
102- Website content in website/src/content/docs/ is auto-generated by prebuild; edit repo sources, not site files
103 
104## Never
105 
106- Never edit .cursor/rules or .gemini/extensions/ directly — these are generated files
107- Never edit website/src/content/docs/ directly — these are generated files; website/ is the fourth generated artifact target (alongside .cursor/, .gemini/, .pi/)
108- Never create a skill without a SKILL.md file and proper verb-noun naming
109- Never push changes without running sync-skills.sh first
110 
111## Token Management
112 
113**Mechanical backstop (e45s03):** `scripts/hooks/token-mgmt-pre-tool-use.sh` blocks oversized tool calls when prose rules are ignored. Wire as a `PreToolUse` hook for `Read`, `Grep`, and `Bash` (alongside `hooks/pre-tool-use.sh` for git safety). Thresholds: Read >100KB, Grep >200 matches without `head_limit`, Bash commands likely to exceed 500 output lines without `rtk`/`sqz compress`. Install snippet:
114 
115```json
116{
117  "hooks": {
118    "PreToolUse": [
119      { "matcher": "Read|Grep|Bash", "hooks": [{ "type": "command", "command": "bash scripts/hooks/token-mgmt-pre-tool-use.sh" }] }
120    ]
121  }
122}
123```
124 
125Context engineering (write/select/compress/isolate — see `docs/references/context-engineering.md`):
126 
127- **Write (token-efficient content):** Short functions (4-20 lines), unique symbol names, headless tests. Don't restate code in comments.
128- **Select (include only what's relevant):** Use `bts_map` for ranked file lists, `survey-context` for phase bootstrap. Don't read files you don't need.
129- **Compress (reduce without losing structure):** Use `bts_compress` or pipe through `sqz compress`. Use `rtk` for build/test/git output (60-99% savings). Prefer `terse-mode` when context is heavy.
130- **Isolate (partition work):** Use `kickoff-branch` for isolated worktrees, `dispatch-agents` for parallel tasks with disjoint scopes, `session-state` for cold-start handoff.
131 
132**Effort classification:** Skills carry an `effort:` frontmatter field (`light` | `standard` | `heavy`). Prefer `light` skills for bootstrap/status checks; reserve `heavy` for epic builds and multi-phase planning.
133 
134- **Auto-Terse**: When a session exceeds 20 turns or the context window feels "heavy" (latency increasing), you MUST switch to `terse-mode` to save tokens.
135- **Context Compaction**: Every 10 turns, summarize the current session state and implementation decisions into a short, high-density note.
136- **Minimal Output**: Prefer text-only output for simple status; use `web_fetch` or `run_shell_command` only for evidence.
137- **Stream Stability**: When writing large files or long documents, output continuously in chunks of ~200 lines. Do not pause. If you need time to process, emit a placeholder comment rather than going silent.
138 
139## Session Start
140 
141Before any task, run this sequence — not optional:
142 
1431. Read `CLAUDE.md` (this file)
1442. Read `CONVENTIONS.md`
1453. Read `specs/state.yaml` if it exists — current session and active epic
1464. Read `specs/release-plan.yaml` if it exists — active release context
147 
148## Agent Rules
149 
150- **Workflow Mandate:** You MUST use the bigpowers skills (e.g., `plan-work`, `develop-tdd`, `craft-skill`) to perform tasks. DO NOT write code directly in response to a user prompt like "build this feature".
151- **Always Green / fix-or-log:** Preflight and CI must be green before forward work. Any reproducible gate failure during unrelated work requires **quick-fix** or **fix-bug** — see CONVENTIONS § Discovered Defects. Never dismiss failures as pre-existing or out of scope.
152- Read specs/ and CONVENTIONS.md before writing code.
153- Write the minimum code that solves the stated problem. Nothing extra.
154- Run tests after every change. Show evidence before declaring done.
155- One clarifying question beats a wrong assumption baked into 200 lines.
156- All written output (plans, specs, investigations) goes in specs/.
157 
158## bts toolchain
159 
160`bts` is installed. Prefer its verbs over ad-hoc shell commands.
161 
162| Task | Command | Avoid |
163|------|---------|-------|
164| Search code | `bts find --print <pattern>` | grep / find / cat |
165| Interactive search | `bts find <pattern>` | manual grep pipes |
166| Compress for context | `bts compress <file>` or `cmd \| bts compress` | summarising by hand |
167| Repo map | `bts map` | listing files by hand |
168| Library docs | `bts docs <lib>` | guessing from training data |
169| Package source | `bts src <pkg>` | git clone |
170| Toolchain health | `bts doctor` | which / command -v |
171 
172**Rules**
173- Search with `bts find` before opening files to locate a symbol or pattern.
174- Pipe anything > 200 lines through `bts compress` before adding to context.
175- Run `bts map` when asked for a repo overview.
176- Use `bts docs <lib>` before answering questions about library APIs. Doc fetches use `scripts/lib/doc-fetch-cache.sh` (ETag-revalidated, 300s TTL — see `context7-mcp` skill, e45s20).
177- If a tool is missing, say so and run `bts doctor` — do not silently substitute.
178 
179<!-- BEGIN rtk-pretooluse-hook (e45s16 — mechanical PreToolUse backstop; remove block to disable) -->
180 
181**RTK hook (installed):** `scripts/hooks/rtk-rewrite.sh` is symlinked into `~/.claude/hooks/` by `bash scripts/install.sh` and registered as a Bash `PreToolUse` hook. It delegates to `rtk hook claude` — prose rules below are a fallback only when the hook is absent.
182 
183<!-- END rtk-pretooluse-hook -->
184 
185<!-- BEGIN sqz-claude-guidance (auto-installed by sqz init; remove this block to disable) -->
186 
187## sqz — Context Compression (READ FIRST)
188 
189sqz is installed in this project. It compresses tool output so large
190files, long logs, and verbose command output cost far fewer tokens.
191There are **two ways** sqz is wired in, and you should prefer each
192one in the situations below.
193 
194### Preferred tools (MCP)
195 
196The `sqz-mcp` server is registered in this project's MCP config. It
197exposes three read-only tools that compress their output through the
198sqz pipeline:
199 
200- **`sqz_read_file`** — read a file from disk and return a compressed
201  view. **PREFER this over the built-in `Read` tool** for any file
202  larger than ~2KB or any file you might read more than once in the
203  same session. Repeat reads return a 13-token `§ref:HASH§` reference
204  instead of the full content.
205 
206- **`sqz_grep`** — search files for a literal string or regex.
207  **PREFER this over the built-in `Grep`** for anything that might
208  match more than a handful of lines. Caps at 200 matches by default;
209  raise with `max_matches` if needed.
210 
211- **`sqz_list_dir`** — list a directory. Skips `.git`, `node_modules`,
212  `target`, `dist`, `build`, `vendor`, `__pycache__` so the output
213  stays focused. **PREFER this over `ls -la` via Bash** when you want
214  to see a project layout.
215 
216The built-in `Read`, `Grep`, `Glob` tools remain available. Use them for:
217- Tiny config files (<1KB) where compression can't help.
218- Byte-exact reads you'll hash or diff (lockfiles, signatures).
219- Globbing (sqz has no glob tool; `Glob` is still the right choice).
220 
221### Bash commands (hooked automatically)
222 
223When you run a shell command through the `Bash` tool, a PreToolUse hook
224rewrites it to pipe output through `sqz compress`. This is transparent:
225you don't need to remember to add anything, but it's useful to know
226that these commands get compressed automatically:
227 
228```bash
229git status           # → git status 2>&1 | sqz compress --cmd git
230cargo test           # → cargo test 2>&1 | sqz compress --cmd cargo
231docker ps            # → docker ps 2>&1 | sqz compress --cmd docker
232kubectl get pods     # → kubectl get pods 2>&1 | sqz compress --cmd kubectl
233```
234 
235The rewrite is skipped for interactive commands (`vim`, `ssh`,
236`python`), compound commands (`a && b`, `a > file.txt`), and anything
237already going through sqz.
238 
239### Escape hatch — when you see a `§ref:HASH§` token
240 
241If tool output contains a `§ref:a1b2c3d4§` token and you need the full
242content it points at, resolve it. Three equivalent ways:
243 
244- Shell: `/Users/danielvm/.local/bin/sqz expand a1b2c3d4` (or paste the whole token
245  `/Users/danielvm/.local/bin/sqz expand §ref:a1b2c3d4§`).
246- MCP tool: call `expand` with `{ "prefix": "a1b2c3d4" }`.
247- To get uncompressed output for one command: prefix it with
248  `SQZ_NO_DEDUP=1` (e.g. `SQZ_NO_DEDUP=1 git log | sqz compress`).
249 
250If the compressed output is actively making the task harder (looping
251on refs, small retries replacing one big read), call the `passthrough`
252MCP tool to get raw text.
253 
254### When NOT to use sqz tools
255 
256- Writing or editing files — use the built-in `Write`/`Edit` tools.
257  sqz has no write tools (by design; see issue #5 follow-up).
258- Running commands interactively or in watch mode.
259- Reading very small files (<1KB) where compression can't help.
260 
261<!-- END sqz-claude-guidance -->
262 
263<!-- rtk-instructions v2 -->
264# RTK (Rust Token Killer) - Token-Optimized Commands
265 
266## Golden Rule
267 
268**Always prefix commands with `rtk`**. If RTK has a dedicated filter, it uses it. If not, it passes through unchanged. This means RTK is always safe to use.
269 
270**Important**: Even in command chains with `&&`, use `rtk`:
271```bash
272# ❌ Wrong
273git add . && git commit -m &quot;msg&quot; && git push
274 
275# ✅ Correct
276rtk git add . && rtk git commit -m &quot;msg&quot; && rtk git push
277```
278 
279## RTK Commands by Workflow
280 
281### Build & Compile (80-90% savings)
282```bash
283rtk cargo build         # Cargo build output
284rtk cargo check         # Cargo check output
285rtk cargo clippy        # Clippy warnings grouped by file (80%)
286rtk tsc                 # TypeScript errors grouped by file/code (83%)
287rtk lint                # ESLint/Biome violations grouped (84%)
288rtk prettier --check    # Files needing format only (70%)
289rtk next build          # Next.js build with route metrics (87%)
290```
291 
292### Test (60-99% savings)
293```bash
294rtk cargo test          # Cargo test failures only (90%)
295rtk go test             # Go test failures only (90%)
296rtk jest                # Jest failures only (99.5%)
297rtk vitest              # Vitest failures only (99.5%)
298rtk playwright test     # Playwright failures only (94%)
299rtk pytest              # Python test failures only (90%)
300rtk rake test           # Ruby test failures only (90%)
301rtk rspec               # RSpec test failures only (60%)
302rtk test &lt;cmd&gt;          # Generic test wrapper - failures only
303```
304 
305### Git (59-80% savings)
306```bash
307rtk git status          # Compact status
308rtk git log             # Compact log (works with all git flags)
309rtk git diff            # Compact diff (80%)
310rtk git show            # Compact show (80%)
311rtk git add             # Ultra-compact confirmations (59%)
312rtk git commit          # Ultra-compact confirmations (59%)
313rtk git push            # Ultra-compact confirmations
314rtk git pull            # Ultra-compact confirmations
315rtk git branch          # Compact branch list
316rtk git fetch           # Compact fetch
317rtk git stash           # Compact stash
318rtk git worktree        # Compact worktree
319```
320 
321Note: Git passthrough works for ALL subcommands, even those not explicitly listed.
322 
323### GitHub (26-87% savings)
324```bash
325rtk gh pr view &lt;num&gt;    # Compact PR view (87%)
326rtk gh pr checks        # Compact PR checks (79%)
327rtk gh run list         # Compact workflow runs (82%)
328rtk gh issue list       # Compact issue list (80%)
329rtk gh api              # Compact API responses (26%)
330```
331 
332### JavaScript/TypeScript Tooling (70-90% savings)
333```bash
334rtk pnpm list           # Compact dependency tree (70%)
335rtk pnpm outdated       # Compact outdated packages (80%)
336rtk pnpm install        # Compact install output (90%)
337rtk npm run &lt;script&gt;    # Compact npm script output
338rtk npx &lt;cmd&gt;           # Compact npx command output
339rtk prisma              # Prisma without ASCII art (88%)
340```
341 
342### Files & Search (60-75% savings)
343```bash
344rtk ls &lt;path&gt;           # Tree format, compact (65%)
345rtk read &lt;file&gt;         # Code reading with filtering (60%)
346rtk grep &lt;pattern&gt;      # Search grouped by file (75%). Format flags (-c, -l, -L, -o, -Z) run raw.
347rtk find &lt;pattern&gt;      # Find grouped by directory (70%)
348```
349 
350### Analysis & Debug (70-90% savings)
351```bash
352rtk err &lt;cmd&gt;           # Filter errors only from any command
353rtk log &lt;file&gt;          # Deduplicated logs with counts
354rtk json &lt;file&gt;         # JSON structure without values
355rtk deps                # Dependency overview
356rtk env                 # Environment variables compact
357rtk summary &lt;cmd&gt;       # Smart summary of command output
358rtk diff                # Ultra-compact diffs
359```
360 
361### Infrastructure (85% savings)
362```bash
363rtk docker ps           # Compact container list
364rtk docker images       # Compact image list
365rtk docker logs &lt;c&gt;     # Deduplicated logs
366rtk kubectl get         # Compact resource list
367rtk kubectl logs        # Deduplicated pod logs
368```
369 
370### Network (65-70% savings)
371```bash
372rtk curl &lt;url&gt;          # Compact HTTP responses (70%)
373rtk wget &lt;url&gt;          # Compact download output (65%)
374```
375 
376### Meta Commands
377```bash
378rtk gain                # View token savings statistics
379rtk gain --history      # View command history with savings
380rtk discover            # Analyze Claude Code sessions for missed RTK usage
381rtk proxy &lt;cmd&gt;         # Run command without filtering (for debugging)
382rtk init                # Add RTK instructions to CLAUDE.md
383rtk init --global       # Add RTK to ~/.claude/CLAUDE.md
384```
385 
386## Token Savings Overview
387 
388| Category | Commands | Typical Savings |
389|----------|----------|-----------------|
390| Tests | vitest, playwright, cargo test | 90-99% |
391| Build | next, tsc, lint, prettier | 70-87% |
392| Git | status, log, diff, add, commit | 59-80% |
393| GitHub | gh pr, gh run, gh issue | 26-87% |
394| Package Managers | pnpm, npm, npx | 70-90% |
395| Files | ls, read, grep, find | 60-75% |
396| Infrastructure | docker, kubectl | 85% |
397| Network | curl, wget | 65-70% |
398 
399Overall average: **60-90% token reduction** on common development operations.
400<!-- /rtk-instructions -->