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 usefulmove/enso --skill review-before-commitgit clone --depth 1 https://github.com/usefulmove/ensoWrote 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/usefulmove/enso/review-before-commit)<a href="https://agentmods.dev/skills/usefulmove/enso/review-before-commit"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/review-before-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/usefulmove/enso/review-before-commit"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/review-before-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 | $0.00049 | $0.00767 |
| Opus 5.5 | $0.00020 | $0.00307 |
| Sonnet 5.5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
review-before-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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Load this skill when:
- A story's implementation is complete and you're about to move/close it
- Before running
git add/git commitat the end of a story - Before
session-persistwhen code changes have been made - You want a final sanity check against behavioral drift
Invoke it explicitly. This is an advisory skill — it does not block execution.
Workflow
Step 1: Gather Evidence
- Read the active story document (the one in
docs/stories/you're closing) - Run
git diffto see what actually changed - Review the story's Acceptance Criteria and Verification sections
Step 2: Check Principles
Run each check. If any fails, report the violation and suggest a fix.
§10.1 Think Before Coding — Did I plan?
- The Approach section was filled out before execution started
- No file modifications happened between "create story" and "complete approach"
- Risks were identified upfront, not discovered during implementation
- If failed: Reopen planning. Do not persist.
§10.2 Simplicity First — Is this the minimum?
- No new abstractions were introduced for single-use code
- No "flexibility" was added that wasn't explicitly requested
- No features beyond the ask were implemented
- If failed: List the speculative additions. Ask the user if they should stay.
§10.3 Surgical Changes — Did I touch only what I must?
- No lines were changed that don't trace directly to the user's request
- No adjacent code was "improved" (refactored, reformatted, commented)
- Dead code created by MY changes was cleaned up
- Pre-existing dead code was NOT removed unless explicitly asked
- If failed: Revert unrelated changes, or flag them for user review.
§10.4 Goal-Driven Execution — Can I verify completion?
- Every acceptance criterion has a checkmark or explicit reason why it's irrelevant
- Verification steps (tests, builds, output checks) were run and passed
- "Done" is not a gut feeling — it has evidence (passing tests, clean build, etc.)
- If failed: Do not close the story. Run the missing verification steps.
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 · 87 lines · 49 tokens per session scan A 53d32cfa3a2f
review-before-commit is a skill published in the GitHub repository usefulmove/enso (2 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 767 once invoked, about $0.0002 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
github-commander
Structured workflows for GitHub issues, PRs, milestones, and code audits with validation gates and HITL checkpoints. Use when assigned a GitHub issue, reviewing a PR, sprinting through a milestone, updating dependencies, or running code audits. Also use when asked to "triage an issue", "review a PR", or "update deps".…
gsd-pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.
github
Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".
harness-pr-reviewer
Checks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.
address-pr-feedback
Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
verification-gate
You MUST use this when work is about to be called complete, done, fixed, ready, or mergeable - before a completion claim, a merge or pull request, a branch finish, or a handoff report.