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 skills/friedbotstudio/baseline/commit-plannernpx skills add friedbotstudio/baseline --skill commit-plannergit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00116 | $0.00859 |
| Opus 5 | $0.00058 | $0.00430 |
| Sonnet 5 | $0.00023 | $0.00172 |
| Haiku 4.5 | $0.00012 | $0.00086 |
Grade A, and why
commit-planner scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commit-planner — single-concern commit splitting
A dirty tree with mixed concerns (a hook fix, a docs edit, an unrelated config tweak) should not land as one commit. This skill proposes a split into single-concern Conventional Commits groups and stops. Execution stays with /commit (Phase 11) under the normal consent gates — one approved group at a time.
This skill is a generator, not a workflow phase. It enters no Track Guard ordering, blocks nothing, and writes nothing outside its report. It is read-only until the user approves the plan, and even then it only hands the approved grouping to the normal commit path.
Method
1. Inventory the dirty tree
Run git status --porcelain and collect {path, status} entries (untracked included). Do not stage anything.
2. Group deterministically
Feed the entries to the helper:
node .claude/skills/commit-planner/inventory.mjs group --json # wraps inventory.mjs -> groupDirtyTree
groupDirtyTree(entries) is pure and deterministic — no fs, no git, no clock; the same entries (in any order) produce the same groups. Each group carries:
type— the Conventional Commit type the group's paths imply (docs,test,chore,feat/fixcandidates surface assrc-typed groups for main context to refine).scope— a path-derived scope hint (top-level dir or hook/skill slug), ornull.paths— the group's member paths. Every input path appears in exactly one group (partition).
Pairing rule: a source file and its paired test (conventional mapping, e.g. .claude/hooks/foo_guard.mjs ↔ tests/foo-guard.test.mjs) always land in the SAME group — a commit that changes behavior carries its test.
3. Refine in main context
The helper's grouping is mechanical. Main context (Article II — decisions live here) refines it: merge groups that are one logical change, pick the final type(scope): subject per group, order the groups (dependencies first), and flag any group that intersects governance surfaces (CLAUDE.md, docs/init/**, .claude/hooks/**) for extra review.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 50 lines · 0 tokens per session scan A 9904a552c1f4
commit-planner is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 116 tokens to every session and 859 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.