Borrowing it
Nothing to install: this file belongs to RipeMangoBox/BITE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RipeMangoBox/BITE/main/.claude/skills/reviewer-stress-test/SKILL.mdgit clone --depth 1 https://github.com/RipeMangoBox/BITEWrote 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/ripemangobox/bite/reviewer-stress-test)<a href="https://agentmods.dev/skills/ripemangobox/bite/reviewer-stress-test"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/reviewer-stress-test/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/ripemangobox/bite/reviewer-stress-test"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/reviewer-stress-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00529 |
| Opus 5 | $0.00026 | $0.00264 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
reviewer-stress-test 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Stress Test
Purpose
Provide a strong reviewer-mode stress test for:
- idea
- roadmap
- full paper draft
Default strictness is strong review. The skill must remain fair and must provide repair paths.
Positioning
This is an evaluative mode, not a co-creation ideation mode.
- Focus: attack assumptions, expose rejection-level risks, test evidence sufficiency.
- Output style: verdict-like risk assessment with fixes.
Evidence protocol
- KB-first: first ground analysis via
papers-query-knowledge-base. - On-demand web checks: search web only for high-risk or uncertain claims (for example novelty/SOTA/parallel work).
- Separate missing evidence from actual invalidity.
Mandatory user clarification
Before final verdict, require the user to state:
- The key difference between this work and the most similar prior works.
- Preferably top-3 nearest works with one-line distinctions.
If this is missing, mark novelty confidence as limited.
Review dimensions
Challenge from multiple angles:
- Problem framing and significance
- Novelty and non-triviality
- Technical soundness
- Experimental rigor (baselines, ablations, statistics)
- Reproducibility and implementation feasibility
- Failure modes, robustness, ethics/bias scope
Output contract
Return structured sections:
- Overall risk verdict (acceptance risk band + confidence)
- Major concerns (rejection-level)
- Minor concerns
- Nearest-work gap check
- Repair paths (for each major concern: minimum actionable steps)
- Re-review checklist (what evidence would change verdict)
Tone and fairness guardrails
- Be rigorous, specific, and evidence-based.
- Do not use dismissive or insulting phrasing.
- Every major concern should include at least one feasible repair action.
Non-goals
- Not for open-ended idea expansion.
- Not for broad roadmap generation from scratch.
Independence
This skill can be used independently and does not depend on outputs from idea-focus-coach or research-brainstorm-from-kb. Users can directly bring a formed idea, roadmap, or paper draft into stress testing.
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.
- 10d ago First seen · 78 lines · 53 tokens per session scan A 48f6ccbb61b4
reviewer-stress-test is a skill published in the GitHub repository RipeMangoBox/BITE (61 stars, last pushed 27d ago), licensed MIT. It adds 53 tokens to every session and 529 once invoked, about $0.0003 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 skills, from other repositories
results-report
A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.
wiki-lint
Audit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs…
wiki-export
Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", "knowledge graph export", "export to…
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
agent-identifier
Use when creating or configuring Claude Code agents and their frontmatter.
wiki-dashboard
Create dynamic, queryable dashboard views of the Obsidian vault using Obsidian Bases or Dataview. Use this skill when the user says "create a dashboard", "vault dashboard", "show all X as a table", "dynamic view", "query my vault", "build a content index", "show me all concepts/entities/projects", or wants a…