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 Ghqqqq/codex-overleaf-link --skill reviewer-responsegit clone --depth 1 https://github.com/Ghqqqq/codex-overleaf-linkWrote 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/ghqqqq/codex-overleaf-link/reviewer-response)<a href="https://agentmods.dev/skills/ghqqqq/codex-overleaf-link/reviewer-response"><img src="https://agentmods.dev/badge/skills/ghqqqq/codex-overleaf-link/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/ghqqqq/codex-overleaf-link/reviewer-response"><img src="https://agentmods.dev/badge/skills/ghqqqq/codex-overleaf-link/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 | $0.00034 | $0.00705 |
| Opus 5.5 | $0.00014 | $0.00282 |
| Sonnet 5.5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Response
Map reviewer comments to evidence in the paper, proposed edits, and reply drafts. Keep missing evidence visible instead of filling it with assumptions.
Workflow
-
Split the reviews into atomic comments with stable IDs R., such as R1.2. Keep the reviewer's own numbering when present; retain the original label when splitting a numbered comment into smaller items.
-
For each comment, look for evidence in the project files. Cite actual source lines as plain-text path:line or path:start-end, for example main.tex:212-230. Do not wrap references in backticks: the panel turns plain-text references into clickable links. If evidence is absent, write "Not found"; distinguish files not read from files searched without a match.
-
Output a compact ledger table with these columns:
ID | Comment | Evidence in the paper | Proposed change | Status
Keep cells short for the narrow panel, with each Comment at most about 12 words. Put necessary explanations below the table. Use only these statuses, adding a short reason:
- Ready to edit: the evidence supports a specific local edit.
- Needs an experiment: new experimental evidence is required.
- Needs author input: facts or a decision must come from the author.
- Unresolved: the comment remains open for another stated reason.
- No change: explain why the current paper already addresses the comment or why a change is unwarranted.
Write the table and explanations in the user's language, translating headings, statuses, and "Not found" accordingly. Keep the IDs unchanged.
-
After the ledger, draft replies only for the comments the user asked about, or for every comment when they requested a full response letter. Write reply drafts in English unless the user asks otherwise. Label each draft with its comment ID and distinguish proposed work from completed work.
-
Finish with one "Next:" line, localized to the user's language, explaining how to apply approved items. For example: Next: after approving R1.2, switch to Auto and send "Apply R1.2".
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.
- today First seen · 66 lines · 34 tokens per session scan A e67791e7cadf
reviewer-response is a skill published in the GitHub repository Ghqqqq/codex-overleaf-link (102 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 705 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 2026-10-30.
Other skills, from other repositories
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
refactor-research-code
Clean research code for public release while preserving reported results. Uses releaseaudit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.
prepare-artifacts
Prepares a reproducibility artifact (code/data) for submission and badging. Use when a researcher says "artifact evaluation", "artifact appendix", "reproducibility", "badge", "Artifacts Available/Evaluated/Functional/Reusable", "Results Reproduced/Replicated", "ACM badging", "USENIX/OSDI/SOSP AE", "SIGMOD ARI"…