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 sidiangongyuan/codex-skills-library --skill rebuttal-response-skillsgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/sidiangongyuan/codex-skills-library/rebuttal-response-skills)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/rebuttal-response-skills"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/rebuttal-response-skills/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/sidiangongyuan/codex-skills-library/rebuttal-response-skills"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/rebuttal-response-skills.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 | $0.00060 | $0.02683 |
| Opus 5 | $0.00030 | $0.01341 |
| Sonnet 5 | $0.00012 | $0.00537 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
rebuttal-response-skills 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebuttal Response Skills
Goal
Produce reviewer-specific responses that are direct, easy to verify, and strictly grounded in the submitted paper or approved rebuttal evidence. Keep internal risk control rigorous without turning the visible response into a stream of disclaimers.
Choose the Workflow
Use the full workflow for a complete rebuttal, multiple reviewers, new evidence or experiments, a meta-review, or a final acceptance audit. Maintain four internal artifact classes in the task's rebuttal directory:
- Exact review archive, such as
reviews.md. - Concern/evidence map with a shared decision ledger, such as
concern_map.md. - One response per reviewer.
- Final audit record, such as
rebuttal_audit.md.
Use the lightweight workflow for a bounded sentence rewrite, one isolated question, or minor formatting. Edit inline and create no files unless the user asks. Preserve the original technical meaning and claim strength by default. The supplied sentence is sufficient for a pure prose edit; ask for context only when clarity would require changing a factual claim, number, quotation, or scope statement.
Read references/response-patterns.md when drafting a full response, integrating experiments, resolving a risk marker, running a blind audit, or performing final format verification.
Establish Sources of Truth
- Treat the complete review text supplied by the user as the review source of truth. If the user later supplies a revised version, use it and record the replacement. Check the platform only when text is incomplete, versions conflict, or the user asks. Do not draft a full response from a review summary; request the exact weaknesses, questions, score, and confidence.
- Read the submitted paper and supplement as the reviewer saw them. Prefer the submitted PDF for claims and values; use source files to locate content only when their submitted status is verified.
- For rebuttal-only work, treat the submission as immutable evidence. Record its hash or version before work and verify it is unchanged at the end. Edit it only under a separate explicit request.
- Determine the official response mode, per-response or shared limit, anonymity rules, Markdown/LaTeX support, and link or attachment policy. Verify current official instructions when the venue is known and the user has not supplied them.
What ships with it
4 files 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 · 261 lines · 60 tokens per session scan A 6decab7b8f5f
rebuttal-response-skills is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 2,683 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 2026-08-31.
Other skills, from other repositories
skills-manager-cli
Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…
superloopy-loop
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.
superloopy-frontend
Use only after explicit Codex $superloopy:superloopy-frontend or Claude Code /superloopy:superloopy-frontend invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task…
say-it-straight
Use only after explicit Codex $superloopy:say-it-straight or Claude Code /superloopy:say-it-straight invocation to make supplied or requested prose direct, concise, and natural without changing facts or protected text.
superloopy-research
Use only after explicit Codex $superloopy:superloopy-research or Claude Code /superloopy:superloopy-research invocation, a research task started with a leading loopy or 루피 (such as loopy research), or an active Superloopy loop explicitly routing a research deliverable here. Evidence-backed Superloopy research…
codex-delegate
Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files"…