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.svg" alt="Measured on agentmods" 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 | $0.02675 |
| Opus 5 | $0.00015 | $0.01337 |
| Sonnet 5 | $0.00006 | $0.00535 |
| Haiku 4.5 | $0.00003 | $0.00267 |
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 today.
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 — 113 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 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 | A new tracked file over the configured ceiling fails; an existing oversized file may hold or shrink but may not grow; 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. |
| changelog-entries | Each COMMIT_GUARDS_CHANGELOG_PATHS fragment is one Markdown list item in a Keep a Changelog section and at most COMMIT_GUARDS_CHANGELOG_CAP characters. |
| prose | A history reference in Markdown named by COMMIT_GUARDS_PROSE_PATHS fails; COMMIT_GUARDS_CHECKS controls whether the lane runs. |
| md-format | A 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-refs | A relative link, a link followed by § and a heading prefix, a <path>.md § Heading or <path>.md#anchor code-span citation, or a decision ID in Markdown named by COMMIT_GUARDS_MD_REFS_PATHS that lands on no tracked file, heading or decision fails. |
| 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
60 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 21 KB
- DEVELOPMENT.md 12 KB
- kendex.settings.toml.example 3.9 KB
- README.md 1.7 KB
- scripts/byte-ceiling 8.7 KB
- scripts/changelog-entries 12 KB
- scripts/comments 14 KB
- scripts/commit-guards 5.3 KB
- scripts/commit-msg 11 KB
- scripts/conflict-markers 3.1 KB
- scripts/install-git-hooks 25 KB
- scripts/lib/atomic-install.sh 6.4 KB runs code
- scripts/lib/changelog-collate.sh 9.7 KB runs code
- scripts/lib/changelog-grammar.sh 10 KB runs code
- scripts/lib/changelog-record-scope.sh 4.1 KB runs code
- scripts/lib/comment-text.sh 11 KB runs code
- scripts/lib/commit-changes.sh 6.3 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 15 KB runs code
- scripts/lib/configured-paths.sh 16 KB runs code
- scripts/lib/helper-body.sh 9.2 KB runs code
- scripts/lib/hook-check.sh 12 KB runs code
- scripts/lib/hooks-path.sh 7.0 KB runs code
- scripts/lib/md-blocks.awk 11 KB
- scripts/lib/md-refs.awk 12 KB
- scripts/lib/md-scope.sh 3.7 KB runs code
- scripts/lib/md-shapes.awk 3.4 KB
- scripts/lib/md-slug.awk 3.8 KB
- scripts/lib/paths.sh 2.9 KB runs code
- scripts/lib/settings.sh 21 KB runs code
- scripts/lib/skill-roots.sh 3.0 KB runs code
- scripts/lib/staged-lines.sh 2.5 KB runs code
- scripts/md-format 4.8 KB
- scripts/md-reflow 6.3 KB
- scripts/md-refs 9.1 KB
- scripts/pre-commit 10 KB
- scripts/prose 7.2 KB
- scripts/suppression-ban 15 KB
- scripts/todo-ban 9.1 KB
- tests/bsd-argv-install.test.sh 5.1 KB runs code
- tests/byte-ceiling.test.sh 18 KB runs code
- tests/changelog-collate.test.sh 15 KB runs code
- tests/changelog-entries.test.sh 38 KB runs code
- tests/changelog-record.test.sh 5.2 KB runs code
- tests/cleanup-scope.test.sh 5.4 KB runs code
- tests/comments.test.sh 32 KB runs code
- tests/commit-msg-amend.test.sh 5.2 KB runs code
- tests/commit-msg.test.sh 43 KB runs code
- tests/conflict-markers.test.sh 8.6 KB runs code
- tests/dispatcher.test.sh 10 KB runs code
- tests/harness-adoption.test.sh 5.2 KB runs code
- tests/index-reads.test.sh 41 KB runs code
- tests/install-git-hooks-check.test.sh 15 KB runs code
- tests/install-git-hooks-hookspath.test.sh 19 KB runs code
- tests/install-git-hooks-scope.test.sh 18 KB runs code
- tests/install-git-hooks.test.sh 37 KB runs code
- tests/lib/harness.bash 2.3 KB runs code
- tests/lib/install-hooks.bash 3.5 KB runs code
- tests/lib/pty.bash 6.8 KB runs code
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.
- today First seen · 113 lines · 30 tokens per session scan C b77a710937ca
commit-guards is a skill published in the GitHub repository vanillagreencom/kendex (74 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 2,675 once invoked, about $0.0002 per session on Opus 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
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
fix-merge-conflicts
Resolve Git merge, rebase, or cherry-pick conflicts by preserving intent from both sides. Use when unmerged paths or conflict markers are present, especially when you must inspect the PR title and description tied to conflicting commits before choosing a resolution.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…