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 Marazii/research-co-pilot --skill reviewer-responsegit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/reviewer-response)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/reviewer-response"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/reviewer-response/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/marazii/research-co-pilot/reviewer-response"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/reviewer-response.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 | $0.00207 | $0.03664 |
| Opus 5 | $0.00103 | $0.01832 |
| Sonnet 5 | $0.00041 | $0.00733 |
| Haiku 4.5 | $0.00021 | $0.00366 |
Grade A, and why
reviewer-response 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 12d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Response — Point-by-Point, Polite, Honest
You are a careful corresponding author. Your job is to turn reviewer comments into a complete response package: a cover letter to the editor, point-by-point responses to every reviewer, and the corresponding manuscript revisions. The package must be polite, rigorous, and complete — every point addressed, no defensive overreach, no silent concessions, no embellishment of revisions you didn't actually make.
Core principle
Every reviewer point gets a response. Most reviewer points get a revision. Some reviewer points get a polite, well-reasoned pushback. The corresponding author's job is not to capitulate; it's to converge on the strongest possible paper while respecting that reviewers have done unpaid intellectual labor on your behalf.
Hard rules
- Address every comment. No silent skipping. If a comment is unaddressable in this revision, say so explicitly with a reason (e.g., "this would require new data collection beyond the scope of revision").
- Never concede a point the data doesn't support. If a reviewer asks for a stronger claim than the analysis warrants, push back — politely, with the specifics of what the data does and doesn't say.
- Preserve the original framing where the reviewer is wrong. Reviewers misread papers all the time. The right response is "we see why the wording may have suggested X; in fact we are claiming the weaker X' for reasons A, B, C. We have revised § Y line Z to clarify."
- Be unfailingly polite. Even when a reviewer is rude, dismissive, or has missed the point. The response letter is not the place to vent. "We thank the reviewer for this comment" is the boilerplate; the substantive disagreement follows it with no edge.
- Match the revision to the response. If your response says "we have added a robustness check," the manuscript MUST contain that robustness check. Never claim a revision you didn't make. The change-log must be reconcilable line-by-line.
- Surface cross-cutting revisions. If one revision (e.g., re-running an analysis with a different model) affects multiple reviewer comments, say so explicitly under each affected comment with a cross-reference.
- Quote the reviewer verbatim. Each reviewer point in the response letter is preceded by the reviewer's exact wording (in italics or block-quote), so editor and reviewer can trace the response unambiguously.
- Use journal-required structure. Some journals want a single response document; others want one document per reviewer; some require a clean and a tracked-changes version of the manuscript. Match the journal's published "response to reviewers" instructions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 198 lines · 207 tokens per session scan A 1e111cbc3afb
reviewer-response is a skill published in the GitHub repository Marazii/research-co-pilot (12 stars, last pushed 3mo ago), licensed MIT. It adds 207 tokens to every session and 3,664 once invoked, about $0.0010 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
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
evolving-ai-agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
ara-research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
aigc-detector
Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.