Commit Guards logo

Commit Guards

Organization
vanillagreencom
commit-guards

Load to add, tune, or debug a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings.

Overview

Publishervanillagreencom
Repositorykendex
Skill namecommit-guards
Stars
80
Forks
31
Bundled files
84
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 84 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vanillagreencom on GitHub. Read the source before you install it.

Installation

Install the Commit Guards AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vanillagreencom/kendex.git /tmp/kendex
mkdir -p .claude/skills
cp -r /tmp/kendex/skills/commit-guards .claude/skills/commit-guards
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Commit Guards in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Commit Guards on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Commit Guards is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Commit Guards

bash
.agents/skills/commit-guards/scripts/commit-guards                   # batch: every enabled check over the whole tree
.agents/skills/commit-guards/scripts/commit-guards all --staged      # the same batch at commit scope
.agents/skills/commit-guards/scripts/commit-guards all --base origin/main # the same batch over a branch's changes (CI)
.agents/skills/commit-guards/scripts/commit-guards todo-ban     # one check by name, flags pass through
.agents/skills/commit-guards/scripts/md-reflow PATH...          # rewrite markdown to the format md-format judges
.agents/skills/commit-guards/scripts/install-git-hooks          # arm the git pre-commit/commit-msg/pre-push shims
.agents/skills/commit-guards/scripts/install-git-hooks --check  # read-only: are the shims still armed?

The checks

CheckVerdict
todo-banAny work marker (TODO, FIXME, HACK, XXX in comment-marker shapes) in a tracked, non-excluded file fails. No baseline.
byte-ceilingA new tracked file over the configured ceiling fails; an existing oversized file may hold or shrink but may not grow; lockfiles are exempt.
suppression-banBlanket lint suppressions fail; reasonless Rust dead or unused allows may only tighten against the baseline.
conflict-markersAn unresolved merge-conflict marker in a tracked, non-excluded file fails.
changelog-entriesEach COMMIT_GUARDS_CHANGELOG_PATHS fragment is one Markdown list item in a Keep a Changelog section and at most COMMIT_GUARDS_CHANGELOG_CAP characters.
proseA history reference in Markdown named by COMMIT_GUARDS_PROSE_PATHS fails; COMMIT_GUARDS_CHECKS controls whether the lane runs.
md-formatA hard-wrapped paragraph or list item, a missing blank line around a heading, fence or list, or a trailing-double-space break in Markdown named by COMMIT_GUARDS_MD_PATHS fails; md-reflow is the remedy.
md-refsA dead relative link, section, content citation or decision reference in selected Markdown fails. COMMIT_GUARDS_MD_REFS_PATHS selects documents; COMMIT_GUARDS_MD_REFS_SOURCE_PATHS selects source comments and TOML strings for § citations. The supported forms are in CHECKS.md § md-refs.
py-namesAn undefined name or a syntax error in a Python file fails, judged by ruff or, where ruff is absent, pyflakes; neither installed while a Python file is selected is exit 2. See CHECKS.md § py-names.
commentsA history reference in the comment text of a source file named by COMMIT_GUARDS_COMMENT_PATHS fails: an issue id (GH_ISSUE_PATTERN), #NNN, or a date. Optional audit; see CHECKS.md § comments.
commit-msgThe header must be type(scope)!: subject within COMMIT_GUARDS_SUBJECT_MAX; a commit touching COMMIT_GUARDS_CHANGELOG_REQUIRED_PATHS also owes a changelog entry or [no-changelog].

Full check shapes and scopes: CHECKS.md.

Exit codes: 0 clean, 1 violations, 2 usage, configuration, or collection error. An unmerged entry in a scanned path is a collection error.

Git hooks

Run scripts/install-git-hooks [--repo PATH] to arm the shims.

Pre-commit order: doc-limits --staged when installed -> preflight --staged when installed -> bot-instructions check --staged when installed -> commit-guards all --staged -> COMMIT_GUARDS_PRE_COMMIT_LOCAL when configured. commit-msg runs the message gate.

pre-push runs doc-limits over the pushed tree and then the batch over what each pushed branch would do to the remote, so a state a replay carried in — a rebase, a cherry-pick, an autosquash, none of which run a commit hook — is judged before the branch leaves the machine. What a ref line deposits decides whether it is judged, so git push origin HEAD is judged like any other branch push; a deletion and a line landing on a tag or a note are skipped, and a line the lane cannot read is refused. Two refusals keep the verdict about the thing being pushed, since every range scope there ends at HEAD, every scan not handed a range reads the index, and every lane reads its tracked policy from the index: a branch whose tip is not HEAD, and an index holding content HEAD does not. Neither consults untracked files or unstaged edits.

The batch runs the enabled checks less the ones this scope leaves nothing for. A check this run hands no scope, whose configured scope then selects from the staged diff, opens no file at push — nothing is staged, which the refusal above makes certain — so it is withheld and named rather than counted clean. Where a range can be established the markdown lanes are handed it under their default touched scope, and judge what the branch changed, so a malformed document or a broken reference that a replay carried in is caught. Where none can be, the whole tree is the scope and those lanes are withheld: that sweep is absolute rather than ratcheted, so imposing it would refuse every push in a repository holding markdown that predates the guard, and choosing it is COMMIT_GUARDS_MD_SCOPE=all, the project's call. A project that has chosen it keeps it under every scope — a range is narrower than that sweep, so the batch hands such a lane --all rather than the range, and a document the range never touched still fails. Which lanes read that setting at all is taken off their own scripts rather than listed, and what it resolves to is asked of the setting's owner.

What the scope rests on: the remote oid git puts on a ref line is read from the destination itself, and it is the only destination-bound evidence a pre-push hook gets. Where it is there, the batch is asked what landing HEAD at that oid would do to it (--against, two dots) rather than what the branch adds over the ancestor the two share — on a force-pushed branch those differ, and only the first is what the destination receives. Where the oid is absent — every branch's first push — the scope is a best-effort local one taken from this repository's refs for the remote, which record a past fetch. After a git remote set-url those refs still describe the previous repository, so an oversized file can read there as pre-existing. Where no boundary can be established at all — a push by direct URL, a push URL those refs do not describe, a branch nothing of which has reached the remote — the scope is the whole tree, where an oversized file is held to its row in the byte baseline: a repository carrying a file that was already oversized when it adopted the package, with no row for it, has such a push refused, and a baseline row, the excludes list or the bypass is the way past. Scope details: DEVELOPMENT.md § The pre-push lane.

Arming and disarming apply to the whole repository. Disarm before removing the skill. Ownership and layering: README.md § Git hooks; install mechanics: DEVELOPMENT.md § Git hook install contract.

Configuration

Exclude immutable first-party sources, including applied SQL migrations, from the comments and prose lanes through their shared excludes lists. Keep preflight’s applied-migration-edited lane enabled as the authority on migration bytes. Set PREFLIGHT_MIGRATION_GLOBS for excluded migration paths outside that lane’s defaults.

KeyDefaultMeaning
COMMIT_GUARDS_CHECKStodo-ban byte-ceiling suppression-ban conflict-markers changelog-entries prose md-format md-refs py-namesBatch check list (commit-msg never batches). Under --skip-unscoped a caller that stages nothing withholds the checks it hands no scope whose configured scope reads only the staged diff.
COMMIT_GUARDS_TODO_EXCLUDEStools/todo-ban-excludestodo-ban exclusion list.
COMMIT_GUARDS_BYTE_CEILING_KB200Byte ceiling in KB.
COMMIT_GUARDS_BYTE_EXCLUDEStools/byte-ceiling-excludesbyte-ceiling exclusion list (declared asset trees).
COMMIT_GUARDS_BYTE_BASELINEtools/byte-ceiling-baselinebyte-ceiling --all baseline: the object size each legacy oversized file is held to.
COMMIT_GUARDS_SUPPRESSION_EXCLUDEStools/suppression-ban-excludessuppression-ban exclusion list.
COMMIT_GUARDS_SUPPRESSION_BASELINEtools/suppression-baseline.tsvBare-allow ratchet baseline.
COMMIT_GUARDS_CONFLICT_EXCLUDEStools/conflict-markers-excludesconflict-markers exclusion list.
COMMIT_GUARDS_CHANGELOG_CAP200Characters per changelog entry.
COMMIT_GUARDS_CHANGELOG_PATHSchangelog.d/*/*.mdSpace-separated globs naming the changelog fragments, matched against the full repo-relative path (* crosses /).
COMMIT_GUARDS_CHANGELOG_RECORDCHANGELOG.mdThe collation destination; empty disables collation.
COMMIT_GUARDS_CHANGELOG_REQUIRED_PATHS(empty)Globs whose change obliges a changelog entry, judged by commit-msg; empty switches the rule off.
COMMIT_GUARDS_PROSE_PATHSSKILL.md */SKILL.md AGENTS.md */AGENTS.md CLAUDE.md */CLAUDE.md workflows/*.md */workflows/*.md agents/*.md */agents/*.md docs/architecture/*.mdSpace-separated globs naming the markdown the prose lane scans, matched against the full repo-relative path (* crosses /).
COMMIT_GUARDS_MD_PATHS*.mdGlobs naming the markdown md-format and md-reflow take under --all.
COMMIT_GUARDS_MD_REFS_PATHSPATHS_DEFAULT in scripts/md-refsGlobs naming the Markdown documents md-refs judges.
COMMIT_GUARDS_MD_REFS_SOURCE_PATHSthe COMMIT_GUARDS_COMMENT_PATHS defaultGlobs naming the source files md-refs reads for § citations in comment text.
COMMIT_GUARDS_MD_EXCLUDEStools/md-excludesExclusion list both markdown lanes honour in every scope, and md-reflow under --staged and --all.
COMMIT_GUARDS_MD_SCOPEtouchedWith no scope flag, touched runs md-format on staged files and md-refs on all configured documents when anything is staged; all checks every matching file. Under touched the batch may hand these lanes a commit range instead (--base REF, --against REF); under all it hands them --all, since a range is narrower than the sweep that setting asks for.
DECISIONS_DIR, DECISION_ID_PREFIX, DECISION_ID_WIDTHdocs/decisions, D, 3The decider skill's scheme, read by md-refs to judge decision IDs; IDs are not judged where the directory is not tracked.
COMMIT_GUARDS_COMMENT_PATHSthe extensions in CHECKS.md § commentsSpace-separated globs naming the source files the comments lane scans, matched against the full repo-relative path (* crosses /); replaces the default.
COMMIT_GUARDS_COMMENT_EXCLUDEStools/comments-excludescomments exclusion list (generated, vendored, and immutable first-party files). GH_ISSUE_PATTERN (the github skill's key) declares the tracker ID shape; empty leaves ID checks inactive.
COMMIT_GUARDS_COMMENT_REFERENCE_TYPESissue-id issue-number dateReference classes the comments lane checks; name at least one type.
COMMIT_GUARDS_COMMIT_TYPESbuild chore ci docs feat fix perf refactor revert style testAccepted commit types.
COMMIT_GUARDS_SUBJECT_MAX72Characters allowed in a hand-written commit header.
COMMIT_GUARDS_PRE_COMMIT_LOCAL(empty)Repo-root-relative executable the pre-commit shim runs last.

Settings follow README.md § Settings. COMMIT_GUARDS_SETTINGS_FILE=/dev/null skips file sources; COMMIT_GUARDS_CHANGELOG_COLLATE=1 is environment-only, authorizes --collate on a clean index and working tree, and lets commit-msg count a record change as the release changelog entry.

Excludes format. pattern<TAB>reason per line (shell glob against the full repo-relative path; * crosses /); a pattern without a reason is a config error. A pattern opening with ! carves its matches back into the scanned set, and wins over every exclusion row whatever the order. To exclude a path that literally begins with !, escape it: \!foo. Baseline format. path<TAB>N, LC_ALL=C sorted, unique paths, N a positive integer: a count for suppression-ban, an object size in bytes for byte-ceiling. Initial suppression baseline: CHECKS.md § suppression-ban. Hook install and removal details: DEVELOPMENT.md.

Generated-file exclusions

Suppression-ban excludes the exact files the render writer lists in .kendex-generated.json. Adopted in-place skills and hooks remain governed because the writer leaves their source out of the inventory. Keep the inventory with the renders; adoption needs no manual ownership carve.

The inventory uses the exclusion list’s index-first read contract. An absent inventory is an empty one: nothing is excluded and every tracked file stays scanned, which is what a project whose items are all in-place, or one installed below the Git root, carries. An unreadable or malformed inventory fails with exit 2; install or refresh kendex at the Git repository root in the main checkout and stage the inventory with the renders. Explicit ! rows still restore matching paths to the scan. Keep non-render exceptions in the reasoned exclusion list.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 24 more files.

Frequently asked questions

What does the Commit Guards AI skill do?

Load to add, tune, or debug a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings.

Why use Commit Guards on TypingMind?

Because you install it once and use it with any model. Commit Guards is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Commit Guards in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vanillagreencom/kendex/tree/main/skills/commit-guards. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Commit Guards?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Commit Guards?

As many as you like. As long as a model supports skills, you can use Commit Guards with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Commit Guards AI skill free?

Yes. It is published on GitHub by vanillagreencom under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇