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 Ar9av/PaperOrchestra --skill literature-review-agentgit clone --depth 1 https://github.com/Ar9av/PaperOrchestraWrote 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/ar9av/paperorchestra/literature-review-agent)<a href="https://agentmods.dev/skills/ar9av/paperorchestra/literature-review-agent"><img src="https://agentmods.dev/badge/skills/ar9av/paperorchestra/literature-review-agent/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/ar9av/paperorchestra/literature-review-agent"><img src="https://agentmods.dev/badge/skills/ar9av/paperorchestra/literature-review-agent.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 | $0.00149 | $0.05007 |
| Opus 5 | $0.00075 | $0.02504 |
| Sonnet 5 | $0.00030 | $0.01001 |
| Haiku 4.5 | $0.00015 | $0.00501 |
Grade A, and why
literature-review-agent 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
23 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.
- references/citation-density-rule.md 2.8 KB
- references/cross-index-verification.md 4.4 KB
- references/discovery-pipeline.md 4.8 KB
- references/exa-search-cookbook.md 9.1 KB
- references/prompt.md 3.2 KB
- references/s2-api-cookbook.md 4.1 KB
- references/tavily-search-cookbook.md 9.9 KB
- references/verification-rules.md 5.4 KB
- scripts/bibtex_format.py 5.2 KB runs code
- scripts/check_cutoff.py 2.2 KB runs code
- scripts/citation_coverage.py 3.1 KB runs code
- scripts/cross_verify.py 12 KB runs code
- scripts/crossref_client.py 6.0 KB runs code
- scripts/dedupe_by_id.py 3.1 KB runs code
- scripts/exa_search.py 5.9 KB runs code
- scripts/levenshtein_match.py 2.1 KB runs code
- scripts/openalex_client.py 6.0 KB runs code
- scripts/pre_dedup_candidates.py 4.9 KB runs code
- scripts/s2_cache.py 3.5 KB runs code
- scripts/s2_search.py 7.0 KB runs code
- scripts/sync_keys.py 4.0 KB runs code
- scripts/tavily_search.py 6.1 KB runs code
- scripts/validate_pool.py 4.8 KB runs code
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 · 454 lines · 149 tokens per session scan A 92be70b7608f
literature-review-agent is a skill published in the GitHub repository Ar9av/PaperOrchestra (653 stars, last pushed 1mo ago), with no licence file. It adds 149 tokens to every session and 5,007 once invoked, about $0.0007 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
proof-checker
A workflow for checking mathematical proofs in LaTeX, finding gaps, fixing the derivations, and reviewing the revised proof again. It also produces an audit report of the checking process.
paper-write
A tool for drafting an academic paper section by section in LaTeX from a paper outline. LaTeX is a text-based system commonly used to format scientific papers and their references.
rebuttal
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
auto-review-loop
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
idea-discovery
A complete research-idea pipeline connects literature review, brainstorming, novelty checking, critical review, and experiment planning.