coulomb/repo-scoping
2
0
Fork 0
generated from coulomb/repo-seed
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refresh agent instruction files

Browse Source
This commit is contained in:
Bernd Worsch
2026-05-18 16:55:53 +02:00
parent 61fa33fc39
commit fd7f25866a
10 changed files with 299 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
.claude/rules/agents.md Normal file
View File

@@ -0,0 +1,20 @@
## Kaizen Agents
Specialized agent personas available on demand via the state-hub MCP.
**Discover:** `list_kaizen_agents()` — returns all agents with name, description, category
**Load:** `get_kaizen_agent("tdd-workflow")` — returns full instructions; read and follow them
Common agents:
| Agent | Category | When to use |
|-------|----------|-------------|
| `tdd-workflow` | testing | Step-by-step TDD8 workflow for any feature |
| `code-refactoring` | quality | Code quality analysis and safe refactoring |
| `test-maintenance` | testing | Diagnose and fix failing tests |
| `requirements-engineering` | process | Prevent interface/mock mismatches upfront |
| `keepaTodofile` | process | Maintain TODO.md during work |
| `project-management` | process | Track status, determine next steps |
| `datamodel-optimization` | quality | Optimize dataclasses and data structures |
All 17 agents: call `list_kaizen_agents()` for the full list.

8
.claude/rules/architecture.md Normal file
View File

@@ -0,0 +1,8 @@
## Architecture
<!-- TODO: Describe the key design decisions and component structure.
Key modules, data flows, external integrations, state machines, etc. -->
## Quick Reference
`~/state-hub/mcp_server/TOOLS.md` — MCP tool reference

38
.claude/rules/first-session.md Normal file
View File

@@ -0,0 +1,38 @@
## First Session Protocol
Triggered when `get_domain_summary("capabilities")` shows **no workstreams**.
The project is registered but work has not yet been structured.
**Step 1 — Read, don't write**
- `~/the-custodian/canon/projects/capabilities/project_charter_v0.1.md` — purpose, scope
- `~/the-custodian/canon/projects/capabilities/roadmap_v0.1.md` — planned phases
- Scan repo root: README, directory structure, existing code or docs
**Step 2 — Survey in-progress work**
Look for TODOs, open branches, half-finished files. Note done vs. started but incomplete.
**Step 3 — Propose workstreams to Bernd**
Propose 1–3 workstreams — each a coherent strand, weeks to months, anchored to a
roadmap phase. **Wait for approval before creating.**
**Step 4 — Create workplan file first, then DB record (ADR-001)**
```
workplans/repo-scoping-WP-NNNN-<slug>.md ← write this first
```
Then register in the hub:
```
create_workstream(topic_id="64418556-3206-457a-ba29-6884b5b12cf3", title="...", owner="...", description="...")
create_task(workstream_id="<id>", title="...", priority="high|medium|low")
```
**Step 5 — Record the setup**
```
add_progress_event(
summary="First session: structured capabilities into N workstreams, M tasks",
event_type="milestone",
topic_id="64418556-3206-457a-ba29-6884b5b12cf3",
detail={"workstreams": [...], "tasks_created": M}
)
```
<!-- Delete or archive this file once past first session -->

8
.claude/rules/repo-boundary.md Normal file
View File

@@ -0,0 +1,8 @@
## Repo boundary
This repo owns **repo-scoping** only. It does not own:
<!-- TODO: List what belongs in adjacent repos, e.g.:
- SSH key management → railiance-infra/
- State hub code → state-hub/
-->

5
.claude/rules/repo-identity.md Normal file
View File

@@ -0,0 +1,5 @@
**Purpose:** repo-scoping - (fill in purpose)
**Domain:** capabilities
**Repo slug:** repo-scoping
**Topic ID:** 64418556-3206-457a-ba29-6884b5b12cf3

84
.claude/rules/session-protocol.md Normal file
View File

@@ -0,0 +1,84 @@
## Session Protocol
State Hub: http://127.0.0.1:8000
**Step 1 — Orient**
Read the offline-safe brief first — it works without a live hub connection:
```bash
cat .custodian-brief.md
```
Then call the MCP tool for richer cross-domain context when MCP tools are exposed:
```
get_domain_summary("capabilities")
```
If MCP tools are unavailable in the current agent session, use the REST API:
```bash
curl -s "http://127.0.0.1:8000/state/summary" | python3 -m json.tool
```
If the hub is offline: `cd ~/state-hub && make api`
**Step 2 — Check inbox**
With MCP tools:
```
get_messages(to_agent="repo-scoping", unread_only=True)
```
Mark read with `mark_message_read(message_id)`. Reply or act on coordination
requests before proceeding.
Without MCP tools:
```bash
curl -s "http://127.0.0.1:8000/messages/?to_agent=repo-scoping&unread_only=true" \
| python3 -m json.tool
curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
-H "Content-Type: application/json" -d '{}'
```
**Step 3 — Scan workplans**
```bash
ls workplans/
```
For each file with `status: ready`, `active`, or `blocked`, note pending
`todo`/`in_progress` tasks.
**Step 4 — Present brief**
1. **Active workstreams** for `capabilities` — title, task counts, blocking decisions
2. **Pending tasks** from `workplans/` + any `[repo:repo-scoping]` hub tasks
3. **Goal guidance** — if `goal_guidance` in summary:
- `needs_workplan`: surface as top action — *"Repo goal '{title}' has no workplan yet"*
- `alignment_warnings`: flag if active work is not aligned with current goal
4. **Suggested next action** — highest-priority open item
5. **SBOM status** — flag if `last_sbom_at` is unset for this repo
If no workstreams: follow First Session Protocol (`first-session.md`).
**During work:** `record_decision()` · `add_progress_event()` · `resolve_decision()`
> State Hub is a *read model*. Bootstrap tools (`create_workstream`, `create_task`)
> are First Session Protocol only. Work structure belongs in repo files (ADR-001).
**Session close:**
With MCP tools:
```
add_progress_event(summary="...", topic_id="64418556-3206-457a-ba29-6884b5b12cf3", workstream_id="<uuid>")
```
Without MCP tools:
```bash
curl -s -X POST http://127.0.0.1:8000/progress/ \
-H "Content-Type: application/json" \
-d '{"topic_id":"64418556-3206-457a-ba29-6884b5b12cf3","workstream_id":"<uuid>","event_type":"note","summary":"what changed","author":"codex"}'
```
If workplan files were modified, ensure the local copy is up to date first:
```bash
git -C <repo_path> pull --ff-only
cd ~/state-hub && make fix-consistency REPO=repo-scoping
```
For repos where implementation runs on a remote machine (e.g. CoulombCore),
use the combined target which pulls before fixing:
```bash
cd ~/state-hub && make fix-consistency-remote REPO=repo-scoping
```
**C-15** (DB task ahead of file) is normal in multi-machine workflows — writeback
will sync the file to match DB. **C-16** (repo behind remote) blocks all writes
until you pull — intentional to prevent clobbering remote progress.

19
.claude/rules/stack-and-commands.md Normal file
View File

@@ -0,0 +1,19 @@
## Stack
<!-- TODO: Fill in language, frameworks, and key dependencies -->
- **Language:**
- **Key deps:**
## Dev Commands
```bash
# TODO: Fill in the standard commands for this repo
# Install dependencies
# Run tests
# Lint / type check
# Build / package (if applicable)
```

28
.claude/rules/workplan-convention.md Normal file
View File

@@ -0,0 +1,28 @@
## Workplan Convention (ADR-001)
File location: `workplans/repo-scoping-WP-NNNN-<slug>.md`
ID prefix: `REPO-WP`
Work items originate as files in this repo **before** being registered in the hub.
Canonical workplan/workstream frontmatter statuses are:
`proposed`, `ready`, `active`, `blocked`, `backlog`, `finished`, `archived`.
Use `proposed` for a newly drafted plan, `ready` after review against current
repo state, and `finished` when implementation is complete. `stalled` and
`needs_review` are derived health labels, not stored statuses.
Closed workplans may be moved to `workplans/archived/` with a completion-date
prefix: `YYMMDD-repo-scoping-WP-NNNN-<slug>.md`. The frontmatter id remains
unchanged; the prefix is only for quick visual reference.
Small opportunistic tasks discovered during another session use **Ad Hoc Tasks**:
`workplans/ADHOC-YYYY-MM-DD.md`, workstream slug `adhoc-YYYY-MM-DD`, and task ids
`ADHOC-YYYY-MM-DD-T01`, `T02`, etc. Use adhocs only for low-risk work completed
directly. Promote anything requiring analysis, design, approval, dependencies, or
multiple planned phases into a normal workplan.
Ecosystem todos from other agents arrive as `[repo:repo-scoping]` hub tasks —
visible at session start. Pick one up by creating the workplan file, then registering
the workstream.
<!-- Ralph Loop rules and HEUREKA sequence: ~/.claude/CLAUDE.md — do not duplicate here -->

172
AGENTS.md
View File

@@ -2,46 +2,44 @@
## Repo Identity
**Purpose:** Repository Scoping — turns Git repositories into reviewable,
source-linked maps of `Ability → Capability → Feature → Evidence`. Deterministic
scanners establish observed facts; LLM-assisted extractors propose interpreted
claims; humans or trusted agents approve registry truth.
**Purpose:** repo-scoping - (fill in purpose)
**Domain:** capabilities
**Repo slug:** repo-scoping
**Topic ID:** `64418556-3206-457a-ba29-6884b5b12cf3`
**Workplan prefix:** `RREG-WP-`
**Domain:** capabilities
**Repo slug:** repo-scoping
**Topic ID:** `64418556-3206-457a-ba29-6884b5b12cf3`
**Workplan prefix:** `REPO-WP-`
---
## State Hub Integration
The Custodian State Hub tracks work across all domains. It runs at
`http://127.0.0.1:8000` (local) or `http://127.0.0.1:18000` when accessed from
a remote machine via tunnel.
The Custodian State Hub tracks work across all domains. Interact via HTTP REST —
there is no MCP server for Codex agents.
Interact via HTTP — there is no MCP integration for Codex agents.
| Context | URL |
|---------|-----|
| Local workstation | `http://127.0.0.1:8000` |
| Remote via tunnel | `http://127.0.0.1:18000` |
### Orient at session start
```bash
# Domain workstreams
# Offline brief — works without hub connection
cat .custodian-brief.md
# Active workstreams for this domain
curl -s "http://127.0.0.1:8000/workstreams/?topic_id=64418556-3206-457a-ba29-6884b5b12cf3&status=active" \
| python3 -m json.tool
# Open tasks for this repo (once workstreams are registered)
curl -s "http://127.0.0.1:8000/tasks/?status=todo" | python3 -m json.tool
# Check inbox
curl -s "http://127.0.0.1:8000/messages/?to_agent=repo-scoping&unread_only=true" \
| python3 -m json.tool
```
Also read `workplans/` directly — the files are the source of truth:
Mark a message read:
```bash
ls workplans/
grep -h "^status:" workplans/RREG-WP-*.md
curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
-H "Content-Type: application/json" -d '{}'
```
### Log progress (required at session close)
@@ -50,27 +48,31 @@ grep -h "^status:" workplans/RREG-WP-*.md
curl -s -X POST http://127.0.0.1:8000/progress/ \
-H "Content-Type: application/json" \
-d '{
"summary": "describe what was done",
"summary": "what was done",
"event_type": "note",
"author": "codex"
"author": "codex",
"workstream_id": "<uuid>",
"task_id": "<uuid>"
}'
```
Include `"workstream_id": "<uuid>"` and `"task_id": "<uuid>"` when known.
Omit `workstream_id` / `task_id` when not applicable.
### Mark a message read
```bash
curl -s -X PATCH "http://127.0.0.1:8000/messages/<message_id>/read" \
-H "Content-Type: application/json" -d '{}'
```
### Update task status (after workstreams are synced)
### Update task status
```bash
curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
-H "Content-Type: application/json" \
-d '{"status": "in_progress"}'
# values: todo | in_progress | done | blocked
```
### Flag a task for human review
```bash
curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
-H "Content-Type: application/json" \
-d '{"needs_human": true, "intervention_note": "reason"}'
```
---
@@ -78,99 +80,83 @@ curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
## Session Protocol
**Start:**
1. `ls workplans/` — note active workplans and their open tasks
2. Check inbox via `GET /messages/?to_agent=repo-scoping&unread_only=true`
3. Check for human-flagged tasks: `GET /tasks/?needs_human=true`
1. `cat .custodian-brief.md` — domain goal and open workstreams (offline-safe)
2. Check inbox: `GET /messages/?to_agent=repo-scoping&unread_only=true`; mark read
3. Scan workplans: `ls workplans/` — note `status: ready`, `active`, or `blocked` files and open tasks
4. Check blocked tasks: `GET /tasks/?needs_human=true`
**During work:**
- Update task status in the workplan file as tasks progress
- For significant decisions, record them: `POST /decisions/`
- Update task statuses in workplan files as tasks progress
- Record significant decisions via `POST /decisions/`
**Close:**
1. Update task statuses in workplan files to match progress
2. Call `POST /progress/` with a summary of what was done
3. If workplan files changed, sync them to the hub DB:
```bash
curl -s -X POST "http://127.0.0.1:8000/repos/repo-scoping/sync" | python3 -m json.tool
```
This runs the ADR-001 consistency check with `--fix` and returns a JSON report.
A `"result": "warn"` with only C-17 is normal (unpushed commits); no action needed.
A `"result": "fail"` means file/DB drift that could not be auto-fixed — read the issues list.
1. Update workplan file task statuses to reflect progress
2. Log: `POST /progress/` with a summary of what changed
3. Note for the custodian operator: after workplan file changes, run from
`~/state-hub`:
```bash
make fix-consistency REPO=repo-scoping
```
This syncs task status from files into the hub DB.
---
## Workplan Convention (ADR-001)
Work items originate as files in this repo, not in the hub. The hub is a
read/cache/index layer.
Work items originate as files in this repo — not in the hub. The hub is a
read/cache/index layer that rebuilds from files.
**File location:** `workplans/RREG-WP-NNNN-<slug>.md`
**File location:** `workplans/REPO-WP-NNNN-<slug>.md`
**Archived location:** finished workplans may move to
`workplans/archived/YYMMDD-REPO-WP-NNNN-<slug>.md`. The `YYMMDD` prefix is
the completion/archive date; the frontmatter `id` does not change.
**Ad Hoc Tasks:** small opportunistic fixes discovered during a session use
`workplans/ADHOC-YYYY-MM-DD.md` with task ids `ADHOC-YYYY-MM-DD-T01`, etc. Use
this only for low-risk work completed directly; create a normal workplan for
anything needing analysis, design, approval, dependencies, or multiple phases.
**Frontmatter:**
```yaml
---
id: RREG-WP-NNNN
id: REPO-WP-NNNN
type: workplan
title: "..."
domain: capabilities
repo: repo-scoping
status: active | done
status: proposed | ready | active | blocked | backlog | finished | archived
owner: codex
topic_slug: foerster-capabilities
topic_slug: ...
created: "YYYY-MM-DD"
updated: "YYYY-MM-DD"
state_hub_workstream_id: "<uuid>" # populated by fix-consistency
state_hub_workstream_id: "<uuid>" # written by fix-consistency — do not edit
---
```
**Task blocks** (one per `##` section):
Use `proposed` for a new draft, `ready` after review against current repo
state, and `finished` after implementation. `stalled` and `needs_review` are
derived health labels, not frontmatter statuses.
```markdown
**Task block format** (one per `##` section):
```
## Task Title
\`\`\`task
id: RREG-WP-NNNN-T01
` ` `task
id: REPO-WP-NNNN-T01
status: todo | in_progress | done | blocked
priority: high | medium | low
\`\`\`
state_hub_task_id: "<uuid>" # written by fix-consistency — do not edit
` ` `
Task description.
Task description text.
```
**Status values:** `todo` → `in_progress` → `done` (or `blocked`)
Status progression: `todo` → `in_progress` → `done` (or `blocked`)
---
## Stack and Commands
**Runtime:** Python 3.x, FastAPI, SQLite (dev) / PostgreSQL (prod)
**Package manager:** pip / uv
```bash
# Install
pip install -e ".[dev]"
# Run dev server
uvicorn repo_scoping.web_api.app:app --reload
# Run tests
pytest tests/
pytest tests/ -k "e2e"
# Check API health
curl http://127.0.0.1:8001/health
```
---
## Repo Boundary
This repo owns: repository ingestion, deterministic scanning, LLM-assisted candidate
extraction, review/approval workflow, registry query and search.
It does NOT own: the Custodian State Hub, other domain repos, deployment infrastructure.
Coordination with other domains goes through the State Hub message inbox.
To create a new workplan:
1. Write the file following the format above
2. Notify the custodian operator to run `make fix-consistency REPO=repo-scoping`
(or send a message to the hub agent via `POST /messages/`)

97
CLAUDE.md
View File

@@ -1,88 +1,11 @@
# CLAUDE.md
# repo-scoping — Claude Code Instructions
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Commands
```bash
# Install
pip install -e ".[dev]"
# Run dev server (port 8001)
uvicorn repo_scoping.web_api.app:app --reload --port 8001
# Run tests
pytest
pytest -k "test_scanner" # filter by keyword
pytest tests/test_web_api.py # single file
# Health check
curl http://127.0.0.1:8001/health
```
## Architecture
The service maps Git repositories to reviewable scope maps using a fixed hierarchy:
```
Scope → Ability → Capability → Feature → Evidence → ObservedFact
```
**Data flow for an analysis run:**
1. `POST /repos/{id}/analysis-runs` triggers the pipeline in `RegistryService.run_analysis()`
2. `GitIngestionService` clones or resolves the repo path
3. `RepositoryMetadataExtractor` reads pyproject.toml / package.json / README
4. `DeterministicScanner` produces `ObservedFact` objects (files, languages, manifests, APIs, etc.)
5. `ContentExtractor` chunks files into searchable segments
6. `CandidateGraphGenerator` builds a draft ability→capability→feature→evidence tree from facts
7. Optionally, `LLMCandidateExtractor` proposes additional candidates (requires `REPO_SCOPING_LLM_ENABLED=true`)
8. Candidates are stored; humans or agents review them via `POST .../candidate-graph/approve`
9. Approved characteristics feed `ScopeGenerator` to produce `SCOPE.md`
**Key source locations:**
| Component | Path |
|-----------|------|
| FastAPI routes + DI | `src/repo_scoping/web_api/app.py` |
| Orchestration | `src/repo_scoping/core/service.py` |
| Frozen dataclasses | `src/repo_scoping/core/models.py` |
| Deterministic scanner | `src/repo_scoping/repo_scanning/scanner.py` |
| Candidate graph builder | `src/repo_scoping/candidate_graph/generator.py` |
| SQLite store | `src/repo_scoping/storage/sqlite.py` |
| Schema migration | `migrations/0001_initial.sql` |
**Storage:** SQLite at `var/repo-scoping.sqlite3` (auto-created). Schema migrations run at startup. Dynamic columns are added to support evidence relationships, classification, and expectation gaps.
**LLM extraction** is optional and disabled by default. Enable with `REPO_SCOPING_LLM_ENABLED=true` plus `REPO_SCOPING_LLM_PROVIDER` and `REPO_SCOPING_LLM_MODEL`. The `llm-connect` sibling package provides the adapter abstraction.
**Semantic search** uses `HashingEmbeddingProvider` by default — deterministic, no external service required.
## Environment Variables
| Variable | Default | Purpose |
|----------|---------|---------|
| `REPO_SCOPING_DATABASE_PATH` | `var/repo-scoping.sqlite3` | SQLite file |
| `REPO_SCOPING_CHECKOUT_ROOT` | `var/checkouts` | Git clone cache |
| `REPO_SCOPING_LLM_ENABLED` | `true` | Enable LLM extraction |
| `REPO_SCOPING_LLM_PROVIDER` | — | e.g. `gemini`, `anthropic` |
| `REPO_SCOPING_LLM_MODEL` | — | e.g. `gemini-2.5-flash` |
| `REPO_SCOPING_STATE_HUB_BASE_URL` | `http://127.0.0.1:8000` | State Hub for coordination |
## State Hub & Workplans
Active work is tracked in `workplans/RREG-WP-*.md` — these files are the source of truth (ADR-001). The Custodian State Hub caches this state; workplan files take precedence.
Session protocol (see `AGENTS.md` for full curl examples):
- **Start:** check `workplans/` status headers and State Hub inbox
- **Close:** update task statuses in workplan files, then `POST /progress/` and sync via `POST /repos/repo-scoping/sync`
Workplan sync warns on C-17 (unpushed commits) — that's normal. A `"result": "fail"` needs investigation.
## Docs
Design decisions and terminology live in `docs/`:
- `docs/terminology.md` — characteristic model definitions
- `docs/scope-md-spec.md` — SCOPE.md format
- `docs/characteristic-evidence-model.md` — evidence target kinds
- `docs/classification-strategy.md` — how characteristics are classified
@SCOPE.md
@.claude/rules/repo-identity.md
@.claude/rules/session-protocol.md
@.claude/rules/first-session.md
@.claude/rules/workplan-convention.md
@.claude/rules/stack-and-commands.md
@.claude/rules/architecture.md
@.claude/rules/repo-boundary.md
@.claude/rules/agents.md