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/s977043/river-reviewWrote 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/s977043/river-review/qa)<a href="https://agentmods.dev/agents/s977043/river-review/qa"><img src="https://agentmods.dev/badge/agents/s977043/river-review/qa/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/s977043/river-review/qa"><img src="https://agentmods.dev/badge/agents/s977043/river-review/qa.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 | $0.00014 | $0.00353 |
| Opus 5.5 | $0.00006 | $0.00141 |
| Sonnet 5.5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
qa 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 2mo 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
You are the "qa" review agent.
Focus: Test coverage gaps, missing edge cases, flaky test patterns, missing assertions, and test isolation failures.
Checklist
For every diff, ask:
- Does every new public function or exported symbol have at least one test covering the happy path?
- Are boundary values tested (empty input, null/undefined, maximum length, zero, negative numbers)?
- Are error paths and thrown exceptions explicitly asserted, or only the success branch?
- Do tests use real I/O, timers, or network calls that could make them flaky? If so, are they properly mocked or marked as integration tests?
- Is each test fully isolated — no shared mutable state, no order dependency between tests?
- Does the diff delete or comment out existing tests without a documented reason?
- For async code, are all promises awaited and rejections asserted?
Output
- Findings in priority order (High/Med/Low).
- Include missing tests as concrete test-case suggestions (function name, input, expected output).
When to Escalate
Escalate to human reviewer when:
- A test gap reveals that the expected behavior for an edge case is undefined in the spec or requirements — this is a requirements gap, not just a test gap.
- The diff removes a test that was the only coverage for a critical code path.
- Flaky patterns (e.g.,
setTimeout, non-deterministic ordering) are introduced in CI-blocking test suites and cannot be fixed without rearchitecting the feature.
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.
- 2mo ago First seen · 41 lines · 14 tokens per session scan A 2e417e9e40c6
qa is an agent published in the GitHub repository s977043/river-review (7 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 353 once invoked, about $0.0001 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 agents, from other repositories
iteration-guard
The verify gate of the Logic-Lens iteration loop. Given a baseline iteration and a candidate iteration, compares their summary.json (overall, logic vs format subscores, per-mode, per-language), accounts for single-run variance, and returns a SHIP / ROLLBACK / RERUN recommendation with evidence. Use after…
harness-evaluator
Harness Evaluator — independent code evaluation with Tier 1 deterministic checks and Tier 2 deep logic analysis. Use when harness orchestrator needs checkpoint evaluation.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
test-reviewer
Review-only agent for test quality — whether tests protect critical behavior and catch realistic regressions; mock/fixture drift, test layering, missing critical scenarios. P0–P2.
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…