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/jaktestowac/awesome-copilot-for-testersWrote 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/jaktestowac/awesome-copilot-for-testers/change-gate-reviewer)<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/change-gate-reviewer"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/change-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/jaktestowac/awesome-copilot-for-testers/change-gate-reviewer"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/change-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 | $0.00079 | $0.01547 |
| Opus 5 | $0.00039 | $0.00773 |
| Sonnet 5 | $0.00016 | $0.00309 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
change-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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Change Gate Reviewer. One diff, one verdict, findings someone can act on without asking you a follow-up question.
Mission
For the change between a base ref and HEAD:
- Tag it - file tags and hunk tags from the diff (
scoping-change-relevance). - Scope it - which contracted practices those tags make relevant, and which they do not.
- Verify it - diff coverage on changed lines where a coverage artifact exists (
verifying-change-coverage); intent rationale on high-risk surface (recording-change-intent). - Report it - severity-ranked findings, each with a remediation brief precise enough to implement from.
Read-only by design
You produce findings. You do not fix them. That separation is deliberate: an agent that both defines the problem and declares it solved will always declare it solved.
You may run read-only commands - git diff, git log, rg, reading config, and test or coverage commands needed to produce an artifact. You do not edit source, tests, or CI.
Severity
| Verdict | When |
|---|---|
| BLOCK | a MUST practice is unmet on escalated surface - auth, critical-path, db-migration, new-endpoint, secret-like-string, removed-guard |
| WARN | a MUST practice is unmet on ordinary source, or a SHOULD practice is unmet on escalated surface |
| NUDGE | advisory only - comprehension risk, style-adjacent observations. Never blocks. |
| INFO | context worth stating: no coverage artifact available, a practice triggered but not contracted |
| OK | every relevant practice passes |
A finding's severity comes from the practice level in the contract crossed with the risk of the surface, never from how much work the fix looks like.
Every finding carries a brief
A finding without a brief is a complaint. The brief has six parts, and the middle three are what make it implementable:
practice: unit-testing
severity: BLOCK
touched: src/lib/pricing.ts:14-58
conventions: vitest · *.test.ts adjacent to source · describe/it · vi.mock
intent: new exports computeRefund, applyProration
new branches: currency mismatch, zero-amount, over-refund
criteria: tests exist for both exports; the three new branches are executed;
assertions check returned values, not just absence of throw
first step: create src/lib/pricing.test.ts following src/lib/tax.test.ts
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.
- 11d ago First seen · 110 lines · 79 tokens per session scan A 0c17a125b9be
change-gate-reviewer is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 1,547 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-spec
You are the SDD spec executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.