Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/receptron/mulmoclaude/precommitgit clone --depth 1 https://github.com/receptron/mulmoclaudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02379 |
| Opus 5 | $0.00000 | $0.01189 |
| Sonnet 5 | $0.00000 | $0.00476 |
| Haiku 4.5 | $0.00000 | $0.00238 |
Grade C, and why
precommit scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- [ ] No shell-specific syntax in npm scripts (`rm -rf`, `cp`). How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Commit Review
Review ALL staged and unstaged changes against the project's coding standards before committing. This checklist covers everything the mechanical hook (yarn format/lint/typecheck/build/test) cannot catch.
Run git diff --stat and git diff first, then check every item below against the actual changes. Report violations with file:line references. If everything passes, say "All checks passed — ready to commit."
1. DRY — No Duplication & Small Functions
- No function or 3+ line block is copy-pasted across files. If the same logic appears twice, it MUST be extracted to a shared helper under
server/utils/orsrc/utils/. - Utility functions are grouped by concern: file ops →
utils/files/, dates →utils/date.ts, strings →utils/slug.ts, JSON →utils/json.ts, types →utils/types.ts, spawn →utils/spawn.ts, network →utils/fetch.ts, markdown →utils/markdown.ts, IDs →utils/id.ts, errors →utils/errors.ts. - No new
makeId(),isRecord(),formatSpawnFailure(),isValidSlug(),extractJsonObject(), or similar that already exists inserver/utils/. - Functions are as small as possible. Each function does one thing. If a function body exceeds ~20 lines, look for extractable sub-steps. Before writing a new helper, grep the codebase — it may already exist.
- Every new function MUST have a corresponding test. No exceptions. If it's exported, it has a test file. If it's private but contains non-trivial logic, extract it as a testable exported pure function.
2. Tests
- Every new exported function has at least one unit test (happy path + error case).
- Every new API endpoint has a route-level test in
test/routes/. - Every
.vuecomponent change that affects template bindings, event handlers, or reactive state has an E2E test or extends an existing one. - Test files mirror source layout:
server/utils/date.ts→test/utils/test_date.ts. - Tests use
node:test+node:assert/strict. External APIs are mocked — tests run without API keys. - Test coverage includes: happy path, edge cases, boundary values, empty/null inputs, error cases.
- No test relies on hardcoded POSIX paths — use
path.join(path.sep, ...)oros.tmpdir().
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 132 lines · 0 tokens per session scan C e7cb463a24f1
precommit is a command published in the GitHub repository receptron/mulmoclaude (343 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,379 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.