Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Light0305/Light-skillsnpx agentmods add skills/light0305/light-skills/light-review-rebuttalWrote 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/light0305/light-skills/light-review-rebuttal)<a href="https://agentmods.dev/skills/light0305/light-skills/light-review-rebuttal"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-review-rebuttal/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/light0305/light-skills/light-review-rebuttal"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-review-rebuttal.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 | $0.00162 | $0.03131 |
| Opus 5 | $0.00081 | $0.01566 |
| Sonnet 5 | $0.00032 | $0.00626 |
| Haiku 4.5 | $0.00016 | $0.00313 |
Grade A, and why
light-review-rebuttal 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 13d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and rebuttal
Build a source-preserving review registry, issue matrix, revision plan, evidence/change map, response draft, commitment ledger, unknown/failure record, and delivery package. Treat prose generation as the last layer, not the first.
Read review-rebuttal-resource-map.md before
a real run. Read
references/workflow_contract.md before
creating or consuming canonical JSON. Read references.md
when selecting review/rule sources. The competitor evidence is
../../docs/competitors/review-rebuttal.md.
Non-negotiable boundaries
- Consume venue-matching's selected handoff and review context. Verify selected
identity,
selected_attimezone,selection_basis, user/delegated authorization, chosen candidate ID, fit/risk row, unmodified rule envelopes, source evidence path/as-of/source IDs, manuscript profile, and PDF path/hash/pages/page size/profile/compliance. Never switch venue, reorder tiers, or turn venueUNKNOWNinto a fact. - Keep reviewer, editor, decision, and meta-review text verbatim in the canonical registry. Atom labels, root causes, strategies, and generated prose are interpretation layers; they never replace source text.
- Record fetch time, source URL/type, round, reviewer ID, attachments and
AVAILABLE|UNKNOWN|UNAVAILABLE|STALE. A 401/403/429/5xx, timeout, login, private invitation or network failure isUNAVAILABLE, not “no review.” - Never invent an experiment, analysis, citation, change, line number,
reviewer identity, venue rule or result.
PLANNEDandIN_PROGRESSmay not be phrased as completed.DONErequires a real change locator; completed experiment/analysis additionally requires verifiable run provenance with a matching SHA-256, not merely a local path. Before marking a response package ready, run the atom/action contract gate so source spans, reconstruction hashes, policy/ethics authorization and perspective-specific self-review are machine-checked rather than trusted. - Paper-writing owns manuscript claims and edits. Result-analysis owns evidence strength. Citation owns new-reference identity and claim support. Figure owns visual honesty. Typesetting owns PDF rebuild/compliance. This skill records and routes work; it does not impersonate those producers.
- Stage 13 critical is narrow: only a routable root cause
(
novelty|experiment|writing) explicitly markedrejection_driving=truewith a complete decision/meta-review/reviewer evidence envelope may become critical. Major labels or an overall Reject alone do not make every comment critical. reviewer_classifyandrerouteproduce advice only. Stop after presenting evidence and alternatives. Runpassport add-back-edgeonly after the user chooses the root cause/back-edge. Never mutate the passport automatically.
What ships with it
18 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.
- agents/openai.yaml 254 B
- references.md 3.0 KB
- references/workflow_contract.md 5.4 KB
- review-rebuttal-resource-map.md 5.3 KB
- scripts/check_commitments.py 8.4 KB runs code
- scripts/experiment_request_gate.py 7.9 KB runs code
- scripts/fetch_openreview.py 11 KB runs code
- scripts/rebuttal_budget.py 6.0 KB runs code
- scripts/review_response_contract.py 31 KB runs code
- scripts/review_workflow.py 46 KB runs code
- scripts/reviewer_classify.py 8.7 KB runs code
- templates/commitment_ledger.json 492 B
- templates/experiment_request.example.json 582 B
- templates/rereview_checklist.md 1.1 KB
- templates/response_letter_template.md 1.2 KB
- templates/response_matrix.md 1.1 KB
- templates/review_input.json 2.0 KB
- templates/review-response-contract.example.json 5.6 KB
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.
- 13d ago First seen · 295 lines · 162 tokens per session scan A e27915c9f71a
light-review-rebuttal is a skill published in the GitHub repository Light0305/Light-skills (620 stars, last pushed 2mo ago), licensed MIT. It adds 162 tokens to every session and 3,131 once invoked, about $0.0008 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
paper-writing
Research paper writing assistant that enforces Arpit Gupta's editorial principles, voice profile, and writing workflow. MANDATORY TRIGGERS: Use this skill whenever the user mentions writing a paper, drafting a section, revising a section, editing a paper, reviewing a draft, rewriting an introduction, writing an…
research-writing
A collection of 30 prompt templates for writing and reviewing scientific papers. It covers tasks such as translating, editing, summarizing research, writing sections, creating figure captions, and preparing reviewer replies.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.