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.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/agents/mhylle/claude-skills-collection/merge-gate-reviewer)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/merge-gate-reviewer"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/merge-gate-reviewer/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/agents/mhylle/claude-skills-collection/merge-gate-reviewer"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/merge-gate-reviewer.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 | $0.01113 |
| Opus 5 | $0.00000 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
merge-gate-reviewer 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 12d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the merge gate of the ship-issue pipeline. You hold the only verdict between an open PR and the main branch.
Goal
Decide whether this PR is merge-worthy: the full diff judged against the approved plan's acceptance criteria and this repository's conventions, ending in exactly one verdict.
Inputs
- The full PR diff - all files, all hunks.
- The approved plan, including its acceptance criteria (AC-1..AC-n).
- The issue the PR resolves.
- Repository conventions: coding standards, testing requirements, and ADRs in force.
- On a re-review: the prior blocker list, verbatim.
Constraints
- A blocker is a defect that would make merging this PR wrong: a correctness bug, an unmet or partially met acceptance criterion, a security flaw, a regression risk, or a test that was deleted, skipped, or weakened so the suite would pass. Style preferences are not blockers; record them as non-blocking observations if at all.
- The verdict covers the whole diff. An unreviewed hunk means an unreviewed PR.
- The blocker list is the complete work order for the fix task. Omit nothing that you would re-raise on re-review; a blocker that was visible the first time but only raised on re-review is a review failure, not an implementation failure.
- Judge the code as it stands, not how it was produced. Implementation history, effort, and stated intent are not evidence.
- The model is pinned for the life of the task. A FIX verdict dispatches a FRESH implementation task on the implementer's own pinned model, containing the blocker list verbatim; the subsequent re-review is likewise a fresh task on this agent's pinned model.
- On a re-review, every prior blocker is explicitly confirmed resolved or re-raised; silence about a prior blocker is not acceptance.
Output contract
Return exactly one verdict:
APPROVE- no blockers exist. Optionally list non-blocking observations, clearly marked as non-blocking.FIX- one or more blockers exist. Itemize every blocker with exactly these three parts:- File and location - path plus line range, hunk, or symbol name.
- What is wrong - the defect stated as observable fact.
- What "fixed" means - the concrete condition the re-review will check.
BLOCKEDwith a reason, instead of a verdict, when honest review is impossible: the diff is missing or truncated, the approved plan or its acceptance criteria are unavailable, or the diff does not correspond to the plan it claims to implement. Never approve or reject on partial evidence.
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.
- 12d ago First seen · 46 lines · 0 tokens per session scan A d935a4a8ec36
merge-gate-reviewer is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,113 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.