Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/commit-guards/SKILL.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/commit-guards)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/commit-guards"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/commit-guards/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/vanillagreencom/kendex/commit-guards"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/commit-guards.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 | $0.00030 | $0.05503 |
| Opus 5.5 | $0.00012 | $0.02201 |
| Sonnet 5.5 | $0.00006 | $0.01101 |
| Haiku 4.5 | $0.00003 | $0.00550 |
Grade C, and why
commit-guards 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 10d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:project-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
Commit Guards
.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
| Check | Verdict |
|---|---|
| todo-ban | Any work marker (TODO, FIXME, HACK, XXX in comment-marker shapes) in a tracked, non-excluded file fails. No baseline. |
| byte-ceiling | Optional binary-size check. Add byte-ceiling to COMMIT_GUARDS_CHECKS to enable it. A new tracked binary file over the configured ceiling fails; an existing oversized binary file may hold or shrink but may not grow; text files and lockfiles are exempt. |
| suppression-ban | Blanket lint suppressions fail; reasonless Rust dead or unused allows may only tighten against the baseline. |
| conflict-markers | An unresolved merge-conflict marker in a tracked, non-excluded file fails; a render is not judged. |
| changelog-entries | Each COMMIT_GUARDS_CHANGELOG_PATHS fragment is one Markdown list item in a Keep a Changelog section. |
| prose | Optional audit of history references in Markdown named by COMMIT_GUARDS_PROSE_PATHS; excluded from the default chain. |
| md-format | A hard-wrapped paragraph or list item, a missing blank line around a heading, fence or list, a trailing-double-space break, or a fence or block left open in Markdown named by COMMIT_GUARDS_MD_PATHS fails; a render is not judged; md-reflow is the remedy. |
| md-refs | Dead references in consumer-authored citing files fail; lock-listed citing files warn unless --strict is set. Skipped sources are one count per reason on the summary line, with a path named only where a judged reference lands on it. A file the lane cannot read is named unjudged and fails nothing, except under --strict. 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-names | An undefined name or a syntax error in a Python file fails, judged by ruff or, where ruff is absent, pyflakes; neither usable while a Python file is selected is a gap notice, exit 0, except under a CI range or --all scan, which refuses. See CHECKS.md § py-names. |
| secrets | A credential gitleaks' default rules match fails, named by path, line and rule id and never by value. Under a diff scope only a match on an added line counts, and a range judges each of its commits. It never runs at push. When a missing or too-old gitleaks passes at a gap notice and when it refuses: CHECKS.md § secrets. |
| comments | A 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-msg | The 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]. |
What ships with it
47 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.
- CHECKS.md 52 KB
- kendex.settings.toml.example 5.8 KB
- README.md 4.4 KB
- scripts/byte-ceiling 18 KB
- scripts/changelog-entries 31 KB
- scripts/comments 13 KB
- scripts/commit-guards 18 KB
- scripts/commit-msg 12 KB
- scripts/conflict-markers 3.7 KB
- scripts/install-git-hooks 39 KB
- scripts/install-gitleaks 3.9 KB
- scripts/lib/atomic-install.sh 6.6 KB runs code
- scripts/lib/changelog-collate.sh 13 KB runs code
- scripts/lib/changelog-grammar.sh 17 KB runs code
- scripts/lib/changelog-record-scope.sh 5.0 KB runs code
- scripts/lib/command-position.sh 13 KB runs code
- scripts/lib/comment-text.sh 16 KB runs code
- scripts/lib/commit-changes.sh 6.5 KB runs code
- scripts/lib/commit-header.sh 1.1 KB runs code
- scripts/lib/commit-parent.sh 5.7 KB runs code
- scripts/lib/common.sh 16 KB runs code
- scripts/lib/configured-paths.sh 22 KB runs code
- scripts/lib/generated-paths.sh 3.9 KB runs code
- scripts/lib/helper-body.sh 14 KB runs code
- scripts/lib/hook-check.sh 20 KB runs code
- scripts/lib/hooks-path.sh 9.1 KB runs code
- scripts/lib/md-blocks.awk 10 KB
- scripts/lib/md-refs.awk 22 KB
- scripts/lib/md-scope.sh 12 KB runs code
- scripts/lib/md-shapes.awk 3.4 KB
- scripts/lib/md-slug.awk 3.8 KB
- scripts/lib/messages.sh 1.7 KB runs code
- scripts/lib/paths.sh 2.9 KB runs code
- scripts/lib/settings.sh 22 KB runs code
- scripts/lib/siblings.sh 5.3 KB runs code
- scripts/lib/skill-roots.sh 4.6 KB runs code
- scripts/lib/staged-lines.sh 3.3 KB runs code
- scripts/md-format 6.8 KB
- scripts/md-reflow 7.1 KB
- scripts/md-refs 25 KB
- scripts/pre-commit 9.9 KB
- scripts/pre-push 27 KB
- scripts/prose 6.6 KB
- scripts/py-names 8.8 KB
- scripts/secrets 15 KB
- scripts/suppression-ban 14 KB
- scripts/todo-ban 9.5 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.
- 10d ago Changed · +1 lines f742b07c434b
- 16d ago Changed · +1 lines 9590cf6cae03
- 20d ago Changed · +1 lines 221d26e64493
- 21d ago Changed · -1 lines 62c157c588c1
- 22d ago Changed · +1 lines d7701cbdd657
- 23d ago Changed · -1 lines 9e6fe590a53a
- 24d ago Changed · +1 lines b021e0f31ccd
- 25d ago Changed · +2 lines c8bb108ae090
- 26d ago Changed d0749e4848eb
- 27d ago First seen · 138 lines · 30 tokens per session scan C 8aeb78c861a1
commit-guards is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 5,503 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.