cc-discipline 2.10.1 → 2.10.2

package/templates/CLAUDE.md

@@ -1,96 +1,96 @@
-# [PROJECT_NAME] — CLAUDE.md
-
-> General discipline rules are auto-injected via `.claude/rules/`. This file is for project-specific information only.
-
----
-
-## Project Overview
-
-- **Project name**: [PROJECT_NAME]
-- **One-line description**: [TODO — what this project aims to achieve]
-- **Tech stack**: [TODO]
-- **Key constraints**: [TODO — e.g., performance requirements, compatibility, security]
-
----
-
-## Project Structure
-
-[TODO — describe directory structure and module responsibilities]
-
-```
-├── src/          ← [TODO]
-├── tests/        ← [TODO]
-├── docs/
-│   ├── progress.md      ← Progress and decision log (maintained by Claude, do not edit manually)
-│   └── debug-log.md     ← Debug session log (maintained by Claude)
-└── .claude/
-    ├── rules/           ← Auto-injected rules
-    ├── hooks/           ← Enforced hooks
-    └── agents/          ← Reviewer & investigator subagents
-```
-
----
-
-## Common Commands
-
-[TODO — build, test, lint, run commands]
-
-```bash
-# Build
-# [TODO]
-
-# Test
-# [TODO]
-
-# Lint / Type Check
-# [TODO]
-
-# Run / Simulate
-# [TODO]
-```
-
----
-
-## Project Tools
-
-<!-- Claude: when you create a helper script, tool, or reusable one-liner during a session,
-     register it here IMMEDIATELY. Don't wait for /commit — do it when you create it.
-     Next session's Claude will thank you. -->
-
-<!-- TEMPLATE:
-### [tool name]
-- **Path**: `path/to/script`
-- **Purpose**: what it does, when to use it
-- **Usage**: `exact command to run [with args]`
-- **Created**: [date] — [why it was needed]
--->
-
----
-
-## Code Style
-
-[TODO — team conventions]
-
----
-
-## Known Pitfalls
-
-[TODO — project-specific gotchas, examples:]
-- [e.g., Module X's interface looks like REST but is actually WebSocket]
-- [e.g., Database migrations must be backwards-compatible]
-- [e.g., Third-party library v2 API has breaking changes, we're pinned to v1]
-
----
-
-## Compact Supplement
-
-When compacting, in addition to general rules (preserve task objectives, progress, decisions), also preserve:
-- [TODO — project-specific context that must be retained]
-
----
-
-## Decision Log
-
-| Date | Decision | Reason | Impact |
-|------|----------|--------|--------|
-| | | | |
+# [PROJECT_NAME] — CLAUDE.md
+
+> General discipline rules are auto-injected via `.claude/rules/`. This file is for project-specific information only.
+
+---
+
+## Project Overview
+
+- **Project name**: [PROJECT_NAME]
+- **One-line description**: [TODO — what this project aims to achieve]
+- **Tech stack**: [TODO]
+- **Key constraints**: [TODO — e.g., performance requirements, compatibility, security]
+
+---
+
+## Project Structure
+
+[TODO — describe directory structure and module responsibilities]
+
+```
+├── src/          ← [TODO]
+├── tests/        ← [TODO]
+├── docs/
+│   ├── progress.md      ← Progress and decision log (maintained by Claude, do not edit manually)
+│   └── debug-log.md     ← Debug session log (maintained by Claude)
+└── .claude/
+    ├── rules/           ← Auto-injected rules
+    ├── hooks/           ← Enforced hooks
+    └── agents/          ← Reviewer & investigator subagents
+```
+
+---
+
+## Common Commands
+
+[TODO — build, test, lint, run commands]
+
+```bash
+# Build
+# [TODO]
+
+# Test
+# [TODO]
+
+# Lint / Type Check
+# [TODO]
+
+# Run / Simulate
+# [TODO]
+```
+
+---
+
+## Project Tools
+
+<!-- Claude: when you create a helper script, tool, or reusable one-liner during a session,
+     register it here IMMEDIATELY. Don't wait for /commit — do it when you create it.
+     Next session's Claude will thank you. -->
+
+<!-- TEMPLATE:
+### [tool name]
+- **Path**: `path/to/script`
+- **Purpose**: what it does, when to use it
+- **Usage**: `exact command to run [with args]`
+- **Created**: [date] — [why it was needed]
+-->
+
+---
+
+## Code Style
+
+[TODO — team conventions]
+
+---
+
+## Known Pitfalls
+
+[TODO — project-specific gotchas, examples:]
+- [e.g., Module X's interface looks like REST but is actually WebSocket]
+- [e.g., Database migrations must be backwards-compatible]
+- [e.g., Third-party library v2 API has breaking changes, we're pinned to v1]
+
+---
+
+## Compact Supplement
+
+When compacting, in addition to general rules (preserve task objectives, progress, decisions), also preserve:
+- [TODO — project-specific context that must be retained]
+
+---
+
+## Decision Log
+
+| Date | Decision | Reason | Impact |
+|------|----------|--------|--------|
+| | | | |

package/templates/docs/debug-log.md

@@ -1,48 +1,48 @@
-# Debug Log
-
-> Maintained by Claude Code during debugging sessions.
-> Prevents repeated dead ends after compact. Prevents mole-whacking.
-> Do not edit this file manually — let Claude maintain it.
-
----
-
-## Active Debug Sessions
-
-<!-- Claude: create a new entry below when starting a debug session -->
-
----
-
-## Debug Entry Template
-
-<!--
-Copy the template below to create a new debug entry:
-
-### [date] — [one-line problem description]
-
-**Symptoms**: [specific error messages or abnormal behavior]
-
-**Reproduction conditions**: [how to trigger the problem]
-
-**Hypothesis list**:
-| # | Hypothesis | Supporting evidence | Contradicting evidence | Status |
-|---|-----------|-------------------|----------------------|--------|
-| 1 | | | | [status] |
-| 2 | | | | [status] |
-| 3 | | | | [status] |
-
-Status values: pending → eliminated / confirmed
-
-**Root cause**: [fill in after confirmed]
-
-**Fix**: [describe the fix and how it addresses the root cause]
-
-**Verification**: [results after fixing]
-
-**Lessons learned**: [what was learned; should CLAUDE.md "Known Pitfalls" be updated?]
--->
-
----
-
-## Closed Debug Sessions
-
-<!-- Claude: move completed entries here -->
+# Debug Log
+
+> Maintained by Claude Code during debugging sessions.
+> Prevents repeated dead ends after compact. Prevents mole-whacking.
+> Do not edit this file manually — let Claude maintain it.
+
+---
+
+## Active Debug Sessions
+
+<!-- Claude: create a new entry below when starting a debug session -->
+
+---
+
+## Debug Entry Template
+
+<!--
+Copy the template below to create a new debug entry:
+
+### [date] — [one-line problem description]
+
+**Symptoms**: [specific error messages or abnormal behavior]
+
+**Reproduction conditions**: [how to trigger the problem]
+
+**Hypothesis list**:
+| # | Hypothesis | Supporting evidence | Contradicting evidence | Status |
+|---|-----------|-------------------|----------------------|--------|
+| 1 | | | | [status] |
+| 2 | | | | [status] |
+| 3 | | | | [status] |
+
+Status values: pending → eliminated / confirmed
+
+**Root cause**: [fill in after confirmed]
+
+**Fix**: [describe the fix and how it addresses the root cause]
+
+**Verification**: [results after fixing]
+
+**Lessons learned**: [what was learned; should CLAUDE.md "Known Pitfalls" be updated?]
+-->
+
+---
+
+## Closed Debug Sessions
+
+<!-- Claude: move completed entries here -->

package/templates/docs/progress.md

@@ -1,72 +1,72 @@
-# Progress & Decision Log
-
-> Maintained by Claude Code during work sessions. Read this file after compact to restore context.
-> Do not edit this file manually — let Claude maintain it.
-
----
-
-## Current Status
-
-- **In progress**: [none]
-- **Last updated**: [none]
-- **Next steps**: [none]
-- **Modified files**: [none]
-
----
-
-## Working Context
-
-<!-- Claude: THIS SECTION IS CRITICAL. After compact, this is all you have.
-     Update this continuously, not as a last-minute save.
-     Everything here should let a post-compact Claude resume at full speed. -->
-
-### Key Commands
-<!-- Build, test, deploy, env setup — anything you'd need to re-run -->
-
-### Current Workflow
-<!-- Step-by-step: what process are you following right now?
-     e.g., "1. Edit schema → 2. Run migrate → 3. Run tests → 4. Check API"
-     Include the exact commands, flags, paths. -->
-
-### Tools & Scripts Developed
-<!-- Any helper scripts, one-liners, or tools created this session.
-     Include the file path and what it does. These are easy to forget. -->
-
-### Environment State
-<!-- What's running? What's configured? What ports? What branches?
-     e.g., "Docker compose up on port 5432, feature/auth branch checked out" -->
-
-### Gotchas Discovered
-<!-- Things that bit you this session. Workarounds found. Traps to avoid.
-     e.g., "pytest must be run from /src not root", "API returns 200 on error" -->
-
----
-
-## Milestones
-
-<!-- Claude: append a record below after completing each milestone.
-     DON'T just write one sentence. Each milestone should capture enough
-     detail that a future session can learn from it, not just know it happened.
-     Use the template below. -->
-
-<!-- TEMPLATE (copy and fill for each milestone):
-
-### [date] — [milestone title]
-
-**What**: [what was accomplished, 2-3 sentences]
-**How**: [approach taken, key files changed, commands used]
-**Why this approach**: [why this way and not another — rejected alternatives]
-**Gotchas**: [what went wrong, what was surprising, workarounds]
-**Verification**: [how we confirmed it works — test output, manual check]
-
--->
-
----
-
-## Key Decisions
-
-<!-- Claude: record decisions and reasoning below when making architectural/design decisions -->
-
-| # | Decision | Reason | Impact Scope | Date |
-|---|----------|--------|-------------|------|
-| | | | | |
+# Progress & Decision Log
+
+> Maintained by Claude Code during work sessions. Read this file after compact to restore context.
+> Do not edit this file manually — let Claude maintain it.
+
+---
+
+## Current Status
+
+- **In progress**: [none]
+- **Last updated**: [none]
+- **Next steps**: [none]
+- **Modified files**: [none]
+
+---
+
+## Working Context
+
+<!-- Claude: THIS SECTION IS CRITICAL. After compact, this is all you have.
+     Update this continuously, not as a last-minute save.
+     Everything here should let a post-compact Claude resume at full speed. -->
+
+### Key Commands
+<!-- Build, test, deploy, env setup — anything you'd need to re-run -->
+
+### Current Workflow
+<!-- Step-by-step: what process are you following right now?
+     e.g., "1. Edit schema → 2. Run migrate → 3. Run tests → 4. Check API"
+     Include the exact commands, flags, paths. -->
+
+### Tools & Scripts Developed
+<!-- Any helper scripts, one-liners, or tools created this session.
+     Include the file path and what it does. These are easy to forget. -->
+
+### Environment State
+<!-- What's running? What's configured? What ports? What branches?
+     e.g., "Docker compose up on port 5432, feature/auth branch checked out" -->
+
+### Gotchas Discovered
+<!-- Things that bit you this session. Workarounds found. Traps to avoid.
+     e.g., "pytest must be run from /src not root", "API returns 200 on error" -->
+
+---
+
+## Milestones
+
+<!-- Claude: append a record below after completing each milestone.
+     DON'T just write one sentence. Each milestone should capture enough
+     detail that a future session can learn from it, not just know it happened.
+     Use the template below. -->
+
+<!-- TEMPLATE (copy and fill for each milestone):
+
+### [date] — [milestone title]
+
+**What**: [what was accomplished, 2-3 sentences]
+**How**: [approach taken, key files changed, commands used]
+**Why this approach**: [why this way and not another — rejected alternatives]
+**Gotchas**: [what went wrong, what was surprising, workarounds]
+**Verification**: [how we confirmed it works — test output, manual check]
+
+-->
+
+---
+
+## Key Decisions
+
+<!-- Claude: record decisions and reasoning below when making architectural/design decisions -->
+
+| # | Decision | Reason | Impact Scope | Date |
+|---|----------|--------|-------------|------|
+| | | | | |

package/templates/memory/MEMORY.md

@@ -1,23 +1,23 @@
-# Project Discipline (cc-discipline framework)
-
-This project has cc-discipline installed. Note the following at the start of each new conversation.
-
-## Three Lines of Defense
-1. **Rules** (`.claude/rules/`) — Auto-injected by file path; editing source code triggers checklists
-2. **Hooks** (`.claude/hooks/`) — Run automatically before/after edits; can block operations (exit 2)
-3. **Agents** (`.claude/agents/`) — Reviewer audits proposals; investigator performs isolated research
-
-## Hook Behavior
-- `pre-edit-guard.sh` — **Blocks source code edits** when there are unverified hypotheses; update docs/debug-log.md first
-- `streak-breaker.sh` — Warns at >=3 edits to the same file, **hard stop** at >=5
-- `post-error-remind.sh` — Injects debugging process reminder when errors are detected (via exit 2 feedback)
-
-## Key Files
-- `docs/progress.md` — Progress log, updated at each milestone; first thing to read after compact
-- `docs/debug-log.md` — Debug log, hypotheses marked "pending"/"confirmed"; affects pre-edit-guard
-
-## Core Discipline
-- Understand before acting; don't lock onto first explanation (>=2 alternative hypotheses)
-- 3 consecutive failures → stop and report
-- Don't mole-whack — repeated edits to the same file means root cause not found
-- Four debugging phases: gather → hypothesize → verify → fix; no skipping steps
+# Project Discipline (cc-discipline framework)
+
+This project has cc-discipline installed. Note the following at the start of each new conversation.
+
+## Three Lines of Defense
+1. **Rules** (`.claude/rules/`) — Auto-injected by file path; editing source code triggers checklists
+2. **Hooks** (`.claude/hooks/`) — Run automatically before/after edits; can block operations (exit 2)
+3. **Agents** (`.claude/agents/`) — Reviewer audits proposals; investigator performs isolated research
+
+## Hook Behavior
+- `pre-edit-guard.sh` — **Blocks source code edits** when there are unverified hypotheses; update docs/debug-log.md first
+- `streak-breaker.sh` — Warns at >=3 edits to the same file, **hard stop** at >=5
+- `post-error-remind.sh` — Injects debugging process reminder when errors are detected (via exit 2 feedback)
+
+## Key Files
+- `docs/progress.md` — Progress log, updated at each milestone; first thing to read after compact
+- `docs/debug-log.md` — Debug log, hypotheses marked "pending"/"confirmed"; affects pre-edit-guard
+
+## Core Discipline
+- Understand before acting; don't lock onto first explanation (>=2 alternative hypotheses)
+- 3 consecutive failures → stop and report
+- Don't mole-whack — repeated edits to the same file means root cause not found
+- Four debugging phases: gather → hypothesize → verify → fix; no skipping steps