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 agentmods add skills/ar9av/paperorchestra/content-refinement-agentnpx skills add Ar9av/PaperOrchestra --skill content-refinement-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/content-refinement-agent)<a href="https://agentmods.dev/skills/ar9av/paperorchestra/content-refinement-agent"><img src="https://agentmods.dev/badge/skills/ar9av/paperorchestra/content-refinement-agent.svg" alt="Measured on agentmods" 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 | $0.00145 | $0.04320 |
| Opus 5 | $0.00072 | $0.02160 |
| Sonnet 5 | $0.00029 | $0.00864 |
| Haiku 4.5 | $0.00015 | $0.00432 |
Grade A, and why
content-refinement-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 5d 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
14 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/ai-failure-modes.md 813 B
- references/da-reviewer.md 3.9 KB
- references/halt-rules.md 6.1 KB
- references/prompt.md 5.7 KB
- references/reviewer-rubric.md 6.8 KB
- references/safe-revision-rules.md 4.8 KB
- references/writing-quality-check.md 720 B
- scripts/apply_worklog.py 3.1 KB runs code
- scripts/concession_guard.py 7.5 KB runs code
- scripts/decision_band.py 3.6 KB runs code
- scripts/score_delta.py 7.2 KB runs code
- scripts/score_trajectory.py 8.6 KB runs code
- scripts/snapshot.py 1.6 KB runs code
- scripts/update_critique_memory.py 11 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.
- 5d ago First seen · 392 lines · 145 tokens per session scan A 808643c5364c
content-refinement-agent is a skill published in the GitHub repository Ar9av/PaperOrchestra (650 stars, last pushed 26d ago), with no licence file. It adds 145 tokens to every session and 4,320 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
vedic-calculator
吠陀占星排盘计算引擎。当用户提供出生时间和地点，需要从零计算星盘数据时触发。输入出生日期、时间、地点，直接输出structureddata.md，跳过JHora排盘和PDF读取流程。当用户提到'直接排盘''计算星盘''不用jhora''快速排盘''算一下'等关键词时触发。也在vedic-reader判断无PDF输入时建议使用。.
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
reaper
Run the full Reaper research pipeline: analyze a paper (optional), review literature, formalize the problem, investigate hypotheses with critique loops, and synthesize a report. Use when given a research goal, optionally with a paper.
analyze-paper
Extract structured information from a research paper: system model, theorem statements, proof techniques, complexity claims, and red flags. Use when asked to analyze, summarize, or review an academic paper.
proof-checker
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants…
experiment-audit
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing…