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 skills add fcakyon/phd-skills --skill reviewer-defensegit clone --depth 1 https://github.com/fcakyon/phd-skillsWrote 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/fcakyon/phd-skills/reviewer-defense)<a href="https://agentmods.dev/skills/fcakyon/phd-skills/reviewer-defense"><img src="https://agentmods.dev/badge/skills/fcakyon/phd-skills/reviewer-defense/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/fcakyon/phd-skills/reviewer-defense"><img src="https://agentmods.dev/badge/skills/fcakyon/phd-skills/reviewer-defense.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 | $0.00071 | $0.01015 |
| Opus 5 | $0.00036 | $0.00508 |
| Sonnet 5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
reviewer-defense 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Defense Methodology
You are helping a researcher prepare for peer review by identifying weaknesses, selecting the strongest results, and drafting responses to likely questions.
Step 1: Vulnerability Analysis
Read the paper and identify weaknesses from a reviewer's perspective:
Technical Weaknesses
- Missing baselines that reviewers would expect
- Evaluation metrics that don't fully capture the contribution
- Assumptions stated without justification
- Scalability concerns not addressed
- Missing error analysis or failure case discussion
Presentation Weaknesses
- Claims stronger than evidence supports
- Missing related work that a reviewer in the area would know
- Unclear methodology (could someone reimplement from the paper alone?)
- Figures that don't clearly convey the intended message
- Inconsistencies between sections
Experimental Weaknesses
- Small dataset size without justification
- Missing statistical significance tests
- No comparison with state-of-the-art on standard benchmarks
- Hyperparameter sensitivity not explored
- No computational cost comparison
Step 2: Venue-Specific Anticipation
Different venues have different review cultures:
Top-tier ML/CV conferences (CVPR, NeurIPS, ICLR, ECCV):
- Expect extensive ablation studies
- Strong baseline comparisons required
- Novelty must be clearly articulated
- Reproducibility is valued
Workshops:
- More tolerant of work-in-progress
- Interesting ideas valued over exhaustive evaluation
- Novel applications of existing methods are acceptable
Journals:
- Expect thorough related work discussion
- Deeper analysis and more experiments than conferences
- Writing quality and organization matter more
Step 3: Question Generation
Generate likely reviewer questions, ranked by probability:
For each question:
- The question — phrased as a reviewer would write it
- Why they'd ask — what triggers this concern
- Can existing data answer it? — yes (point to specific data) or no (new experiment needed)
- Draft response — if answerable, write a concise response
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 · 133 lines · 71 tokens per session scan A 99a87d2e4a2f
reviewer-defense is a skill published in the GitHub repository fcakyon/phd-skills (389 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 1,015 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 skills, from other repositories
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
write-detection-rule
This skill teaches Claude Code how to write detection rules for the AI Traffic Control rule engine. Read this before creating or modifying anything in rules/. The full rule schema is Rule in packages/schema/src/zod/rule.ts — it is the source of truth for every field below.
aka-dashboard
Launch the AKA web dashboard in your browser (reads your local store).
aka-health
Show AKA detection activity and local security posture.
aka-audit
Show AKA's recent enforcement decisions.
error-handling
Result pattern, ProblemDetails (RFC 7807), global exception boundaries, and typed error records for .NET APIs.