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 mattmre/EVOKORE-MCP-PUBLIC --skill setup-pre-commitgit clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLICWrote 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/mattmre/evokore-mcp-public/setup-pre-commit)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/setup-pre-commit"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/setup-pre-commit/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/mattmre/evokore-mcp-public/setup-pre-commit"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/setup-pre-commit.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 | $0.00067 | $0.02653 |
| Opus 5.5 | $0.00027 | $0.01061 |
| Sonnet 5.5 | $0.00013 | $0.00531 |
| Haiku 4.5 | $0.00007 | $0.00265 |
Grade A, and why
setup-pre-commit 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Pre-Commit Hooks
Set up (or extend) the EVOKORE pre-commit chain: Husky + lint-staged + Prettier + typecheck + a fast-failing integration-test slice. Detect the existing setup before writing anything; if the repo already has Husky configured, this skill is an UPLIFT (extend, never overwrite).
When to use this skill
Use when an operator asks to install pre-commit hooks, set up Husky, configure lint-staged, add commit-time formatting / typechecking / testing to an EVOKORE-style TypeScript repo, or extend an existing pre-commit chain that's already partially configured.
Trigger phrases that should activate this skill:
- "set up pre-commit hooks"
- "install Husky"
- "add lint-staged"
- "extend the pre-commit chain"
- "wire Prettier into commits"
- "add a typecheck pre-commit step"
Do not use this skill for:
- CI / GitHub-Actions pre-merge gates (those are separate from local pre-commit hooks; use a CI-focused skill).
- Bypassing the pre-commit hook (
git commit --no-verify) — see "Bypass and debugging" below. - Repos that aren't TypeScript-based and Node-toolchain compatible — adapt manually instead of running this skill blindly.
Adapted From Upstream
This skill is adapted from mattpocock/skills @ 90ea8eec03d4ae8f43427aaf6fe4722653561a42 / setup-pre-commit/SKILL.md, MIT licence (c) 2026 Matt Pocock. Upstream attribution and licence text live in the repo-root NOTICE and at SKILLS/upstream/mattpocock-skills/LICENSE.
The upstream provides a clean greenfield install. EVOKORE's port adds: detection, uplift (no silent overwrite), an EVOKORE-style integration-test slice on commit, a typecheck step keyed off npm run build when no typecheck script exists, and a damage-control-aware bypass note. The upstream content remains in the read-only SKILLS/upstream/mattpocock-skills/ submodule and is not indexed by SkillManager.
EVOKORE-Specific Adaptations
- Detect-first, write-second. Inspect
package.jsonforhusky/lint-stagedkeys, check.husky/directory, and read any.prettierrc*or.lintstagedrc*files before writing anything. If any are present, surface the diff and uplift; do not silently overwrite. - Integration-test slice on commit. Upstream runs
npm run test(the full suite) on every commit. EVOKORE's full vitest suite (~2053 tests across 121 files) is too slow for pre-commit, so the EVOKORE pre-commit runs onlynpx vitest run --bail=1 tests/integration/(98 integration tests, sub-minute on the dev box). Full-suite gating moves to CI. - Typecheck graceful fallback. Upstream calls
npm run typecheck. EVOKORE'spackage.jsonexposesnpm run build(which isnpx tsc) as the typecheck path. Iftypecheckscript is absent, the hook usesnpx tsc --noEmitdirectly so the commit doesn't emitdist/artefacts. - Damage-control-aware bypass note.
git commit --no-verifyis the standard escape hatch but EVOKORE's damage-control hook (scripts/hooks/damage-control.js) may flag it under DC-rules. The skill documentsnpx lint-staged --no-stashas the debug path instead of teaching--no-verify. - Composition. Terminal skill — no
next, invoke X skillchain. Once installed, the hook runs in-process on every git commit; nothing further to orchestrate.
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 · 171 lines · 67 tokens per session scan A ef9181537ce8
setup-pre-commit is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 2,653 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
repository-manager-gate-execution
Run and inspect the two-tier (fast/heavy) pre-commit gate across repos via rmgates, and validate a fix without re-running the whole wave: run to populate the durable gate ledger, retest to narrow a re-run to only the hooks the ledger last recorded failing (with automatic full-wave escalation on an all-pass), and…
eg-precommit-review
Run a Codex-native pre-commit independent-review loop on pending changes.
oo-bitbucket
Bitbucket (bitbucket.org). Use this skill for ANY Bitbucket request — reading, creating, updating, and deleting data. Whenever a task involves Bitbucket, use this skill instead of calling the API directly.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
ci-cd
CI/CD pipelines for GitHub Actions and Docker-based deployments — lint, test, build, push, deploy stages; environment secrets; branch-gated workflows; health-check rollbacks; and PM2/systemd service restarts.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.