AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Cm

skill-ctx42-skills-cm · by ctx42

>

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-ctx42-skills-cm

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-ctx42-skills-cm)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Cm? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Commit Message Formatting

Invocation

  • With commit hash: generate from that commit's diff.
  • Otherwise: generate from the current staged/unstaged diff.

Always derive the message from the diff only.

Arguments

Detect from the user's words; they combine (e.g. micro apply). Default (none given): full-length message, presented without committing.

Verbosity — mutually exclusive, default full length:

  • micro → summary line only, no body. Add ! + BREAKING CHANGE: footer

only when the change is breaking.

  • mini → summary line plus one short paragraph explaining the single

most important why. Refs: only if a breaking change applies.

Commit control:

  • apply → commit the generated message directly via heredoc without asking —

git commit, or git commit --amend for a hash invocation.

Describe changes only

Write for any reader of git log, not for someone who sat in planning or review. They only see the diff and the message.

  • State what changed and why in product/code terms (bugs fixed,

behavior, API, tests).

  • Match detail to reader impact. Describe user-facing changes (behavior, API,

bug fixes, CLI/output) precisely; give mechanical cleanups (lint, formatting, renames, dep bumps, test tweaks) a one-sentence summary, not a per-edit account. When a commit mixes both, lead with the user-facing change and fold the cleanup into one closing sentence.

  • A body is optional. If the summary line already conveys the change and

there is nothing user-facing to explain, omit the body entirely rather than manufacturing detail.

  • Do not reference internal process the reader cannot know — remediation

phases, review plans, skill names, "as discussed", ticket/session context, project milestones ("phase 1"), or tmp/*-plan.md paths — unless the diff itself only touches those files.

  • Prefer concrete symbols and files: ` TargetNameFromContext `,

` Prepare `, not umbrella slogans that hide the actual edits.

If the diff mixes unrelated edits (e.g. IDE config + library fix), say so in the body or ask to split commits—still without process jargon.

Structure

[()][!]: 

[body]

[BREAKING CHANGE: ]
[Refs: , ...]

Summary Line

  • Type: feat, fix, refactor, perf, test, docs, style, build,

ci, chore, revert

  • Scope: optional, short noun
  • Description: imperative, lowercase, no period, ideally ≤ 50 chars (hard 72)

Breaking Changes

If the change affects exported symbols or observable behavior for callers:

  • Add ! in the summary.
  • Add mandatory BREAKING CHANGE: footer describing the impact and migration.

Body (Kernel Style)

  • Wrap at 72 columns.
  • Imperative mood.
  • Explain why the change was made (the diff shows what).
  • Use backticks for symbol references: ` xrr.FieldErrors `,

` WithCause `.

  • When referencing prior commits: Commit ("summary") ...

High-clarity standard: Write bodies with godoc-level precision — the smallest body that fully explains the user-facing change and its motivation.

Footers

Only two are allowed:

  • BREAKING CHANGE: ... (when ! is used)
  • Refs: [, ...]

Omit all other trailers.

Never add an AI Co-Authored-By trailer (e.g. Co-Authored-By: ).

Output

Present the full message in a fenced code block with zero leading whitespace on every line.

The message is deliverable. Run git commit / git commit --amend (via heredoc) only when the invocation asks to commit or amend — the apply argument, or wording like "and amend it". Otherwise, never propose committing; the user decides when.

Report tersely: no preamble or narration; state each fact once; don't restate output the user can already see.

Self-learning

Read this skill's lessons and obey them: sibling LESSONS.md, else $HOME/.agent-data/ctx42-skills/lessons/craft/cm.md when this directory is read-only. On a correction or self-caught mistake, append a one-line rule to whichever is writable (creating it) and report where.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.