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 uqeu/estelle-cli --skill commit-guardgit clone --depth 1 https://github.com/uqeu/estelle-cliWrote 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/uqeu/estelle-cli/commit-guard)<a href="https://agentmods.dev/skills/uqeu/estelle-cli/commit-guard"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/commit-guard/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/uqeu/estelle-cli/commit-guard"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/commit-guard.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 | $0.00282 |
| Opus 5.5 | $0.00000 | $0.00113 |
| Sonnet 5.5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
commit-guard 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 1mo 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.
What it actually says
commit-guard
Estelle's commit-time hygiene gate. Cheap, fast, and local — the tree is green before the commit lands, not after CI catches it.
Procedure
- Scope to staged — diff
--cachedto get exactly the files entering the commit; run everything against that set, not the whole repo. - Format — run the formatter on staged files and re-stage the results; a formatting-only diff never reaches review.
- Lint — run the linter on the staged set; block on errors, surface warnings.
- Typecheck — run the type/static checker; a type error is a hard block.
- Affected tests — map changed files to their tests and run only those (fast path); on any failure, abort the commit with the failing line.
- Block or pass — any red step stops the commit and reports the single reason; all green lets it through untouched.
Output
A pass/fail verdict at commit time with the one check that failed. Serves everyday hygiene; hand off to verify-gate for the deeper pre-PR gate.
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.
- 1mo ago First seen · 20 lines · 0 tokens per session scan A 26db3a536896
commit-guard is a skill published in the GitHub repository uqeu/estelle-cli (0 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 282 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 2026-09-12.
Other skills, from other repositories
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
issue-to-pr
Implement one bounded repository issue with normal host tools, prove the tested change through one scafld finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.
cocosearch-commit
Use when committing changes — analyzes staged (or unstaged) diffs with CocoSearch semantic search and dependency impact to generate comprehensive Conventional Commit messages. Reviews changes thoroughly, then asks user to approve, edit, or abort the commit.
test-then-commit
Implements a small change and commits it. Use when the user asks for a quick fix with a commit.
loop-gh-pr
A recipe for a scheduled GitHub pull-request watcher. It checks open pull requests for new activity and prepares read-only review drafts without posting comments or merging anything.
git-iris
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…