Skip to content

✂️ chore(claude.md): drop Code style section — bro doesn't write code#125

Merged
ZaxShen merged 1 commit into
devfrom
chore/claude-md-drop-code-style
Apr 26, 2026
Merged

✂️ chore(claude.md): drop Code style section — bro doesn't write code#125
ZaxShen merged 1 commit into
devfrom
chore/claude-md-drop-code-style

Conversation

@ZaxShen
Copy link
Copy Markdown
Contributor

@ZaxShen ZaxShen commented Apr 26, 2026

Per user review on PR #124: the # Code style section in CLAUDE.md duplicated content already in the code-quality and git-conventions skills.

git-conventions has agent: bro, swe, pr-reviewer in its frontmatter so it auto-loads for whoever needs it. code-quality is similarly shared. Bro almost never writes code (Direct Mode is the narrow exception, ≤3 lines), so 'Self-documenting code' was misplaced.

CLAUDE.md: 149 → 144 lines.

Per user review: bro is a planner/router, not a code writer. The
'Self-documenting code' rule applies to SWE, not bro. The commit-message
rule lives in the git-conventions skill (frontmatter `agent: bro, swe,
pr-reviewer` auto-loads it for all three roles when needed).

CLAUDE.md 149 → 144 lines.
@ZaxShen ZaxShen merged commit f177a48 into dev Apr 26, 2026
5 checks passed
@ZaxShen ZaxShen deleted the chore/claude-md-drop-code-style branch April 26, 2026 21:37
ZaxShen added a commit that referenced this pull request Apr 26, 2026
…rotocol to skills/docs (#126)

User feedback: 'audit every single word' — CLAUDE.md is loaded EVERY
turn, must contain only what bro needs every turn (trigger, identity,
routing, reactive skills lookup). Detail and reference moved out.

Extracted:

- 'Subagent prompt precedence' (4 lines) — DELETED. Subagent prompts
  declare themselves; CC handles dispatch automatically.
- 'Two-layer agent model' (5 lines) → new docs/AGENTS.md.
- 'Forbidden tools' detail (5 lines) → expanded existing
  tmb_mcp-error-handling skill (now also covers policy-key writes).
- First-action chain rationale paragraph (3 lines) → compressed to
  the section header itself ('no exceptions, no shortcuts').
- 'Bro verification' + 'Tool-call batching' detail (5 lines) → already
  documented in planning skills; CLAUDE.md now points there.
- 'Direct ops' verbose section (3 lines) → folded into routing table
  as one row.
- 'Concerns + second opinions' (8 lines) → new tmb_concerns-protocol
  skill (procedural, loads on demand when bro disagrees).
- 'Reference' pointer block (7 lines) → new docs/REFERENCE.md.

Net: 268 → 99 lines (63% reduction over 3 PRs: #124, #125, this one).

What's left in CLAUDE.md:
- Trigger rule (when bro activates) — must be every turn
- Identity (compressed Role) — must be every turn
- MCP caller-id rule (every-turn rule)
- First-action chain (mandatory routine on every triggered message)
- Routing table (decision tree)
- Code-touching ask chain (the planning workflow diagram)
- Reactive skills lookup (so bro knows what to load when)
- Catchphrase + Communication style (identity)
- Reference pointer (2 lines pointing at docs/)

Approaching the 60-line aspirational target — further compression
would gut essential routing.

Co-authored-by: Zax Shen <ZaxShen@users.noreply.github.com>
ZaxShen added a commit that referenced this pull request May 20, 2026
📝 docs(architecture): add UI.md — AskUserQuestion modes inventory (#125)

See merge request trustmybot/plugin!43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant