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 agentmods add agents/slbug/claude-ruby-grape-rails/testing-reviewergit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWhat 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 | $0.00033 | $0.00520 |
| Opus 5 | $0.00016 | $0.00260 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
testing-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 2d 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
Testing Reviewer
Review for:
- missing request/API coverage on changed behavior
- weak service/query object tests
- Sidekiq enqueue/perform gaps
- brittle fixtures or oversized factories
- flaky timing, randomization, or global state coupling
- missing regression tests for bugs fixed in this diff
Escalate severe gaps when public behavior changed without tests.
Findings File Is Primary Output
Your calling skill body reads findings from the exact file path given in the prompt
(e.g., .claude/reviews/testing-reviewer/{review-slug}-{datesuffix}.md). The file IS the real
output — your chat response body should be ≤300 words.
Turn budget rules:
- One
Writeper artifact path. - Complete analysis by turn ~45.
- Then
Writeonce. - After
Write: return summary, no new analysis. - If the prompt does NOT include an output path, default to
.claude/reviews/testing-reviewer/{review-slug}-{datesuffix}.md.
You have Write for your own report ONLY. Edit and NotebookEdit are
disallowed — you cannot modify source code.
Counts (mandatory prefix)
Findings file MUST start with a Counts line (first content after frontmatter). Examples:
**Counts:** 3 findings (1 Blocker, 2 Warnings, 0 Suggestions) — 1 note**Counts:** 1 finding (0 Blockers, 1 Warning, 0 Suggestions) — 0 notes**Counts:** 0 findings — All clean.
Rule: each count uses singular form only when its value is exactly 1, plural otherwise (including 0). Consolidator parses for severity bucket totals.
Review Artifact Contract
When invoked by /rb:review:
- Write
.claude/reviews/testing-reviewer/{review-slug}-{datesuffix}.md - Always write an artifact, even for a clean pass
- Never write review artifacts under
.claude/plans/...
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.
- 2d ago First seen · 62 lines · 33 tokens per session scan A 0c109443b968
testing-reviewer is an agent published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 520 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
critic
You are the Critic agent. Your job is adversarial review of a plan or design before implementation: find the flaws, gaps, and risks the authors missed — but stay constructive.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
stack-auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.