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 skills add notorious-ai/claude-plugins --skill planning-commitsgit clone --depth 1 https://github.com/notorious-ai/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/notorious-ai/claude-plugins/planning-commits)<a href="https://agentmods.dev/skills/notorious-ai/claude-plugins/planning-commits"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/planning-commits/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/notorious-ai/claude-plugins/planning-commits"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/planning-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.02423 |
| Opus 5 | $0.00000 | $0.01211 |
| Sonnet 5 | $0.00000 | $0.00485 |
| Haiku 4.5 | $0.00000 | $0.00242 |
Grade A, and why
planning-commits 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Commits
Plan the sequence of commits for any non-trivial changeset before writing code, and before drafting commit messages. The skill's output is a plan: a numbered list where each entry states one commit's scope in a single sentence and the context that motivates it.
Commit-message-writing skills consume this plan one entry at a time. Defer all message phrasing to the appropriate writing skill — in a Go-centric repository, golang-dev:committing. Planning stops at scope and context; naming the commit is a separate concern handled later.
Core Principles
A commit plan satisfies three facets together — atomic, fine-grained, incremental:
- Atomic. Group changes by value (user-facing capability, feature, single decision), not by syntactic category (all types, all interfaces, all handlers). Each commit advances one identifiable piece of value that can be reverted, evaluated, or rebased in isolation from its neighbours.
- Fine-grained. Each commit lands one reviewable change. The test is reviewability, not file count: a two-line diff can be fine-grained, a fifty-file diff is not, regardless of how small each edit is.
- Incremental. Build the final value over a planned sequence. Start with a skeleton; layer capabilities; never forward-reference symbols or behaviours that do not yet exist on the branch.
For the full definitions, including the value-vs-syntactic distinction and the decision-rationale-layering benefit, consult references/triad.md.
Reference Files
| File | Contains | Load When |
|---|---|---|
references/triad.md |
Full definitions of atomic, fine-grained, incremental, with the value-vs-syntactic distinction | First time the skill triggers in a session |
references/plan-shape.md |
Shape of a plan entry, hand-off to the message-writing skill, worked mini-example | Before producing the plan deliverable |
When to Plan
Plan commits proactively at the earliest signal that the work ahead is non-trivial:
What ships with it
16 files 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.
- examples/antipattern-by-layer.md 2.7 KB
- examples/antipattern-by-mechanical-layer.md 2.6 KB
- examples/antipattern-by-symbol-kind.md 2.7 KB
- examples/antipattern-flags-up-front.md 1.9 KB
- examples/antipattern-trailing-docs-dump.md 2.3 KB
- examples/antipattern-trailing-format-dump.md 2.7 KB
- examples/decision-rationale-layering.md 2.7 KB
- examples/dependency-adoption-isolated.md 2.4 KB
- examples/docs-with-feature.md 2.3 KB
- examples/flags-grow-with-features.md 1.7 KB
- examples/go-mod-get-before-use.md 2.6 KB
- examples/go-mod-tidy-first.md 2.4 KB
- examples/siblings-by-decision.md 2.3 KB
- examples/skeleton-first.md 1.3 KB
- references/plan-shape.md 2.6 KB
- references/triad.md 2.5 KB
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.
- 9d ago First seen · 171 lines · 0 tokens per session scan A 1406bd7cb9f0
planning-commits is a skill published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,423 tokens. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…