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 federicodeponte/opendraft --skill autonomous-researchgit clone --depth 1 https://github.com/federicodeponte/opendraftWrote 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/federicodeponte/opendraft/autonomous-research)<a href="https://agentmods.dev/skills/federicodeponte/opendraft/autonomous-research"><img src="https://agentmods.dev/badge/skills/federicodeponte/opendraft/autonomous-research/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/federicodeponte/opendraft/autonomous-research"><img src="https://agentmods.dev/badge/skills/federicodeponte/opendraft/autonomous-research.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 | $0.00144 | $0.07850 |
| Opus 5.5 | $0.00058 | $0.03140 |
| Sonnet 5.5 | $0.00029 | $0.01570 |
| Haiku 4.5 | $0.00014 | $0.00785 |
Grade A, and why
autonomous-research 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 15d 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 — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Research
Turns one topic line into a finished paper with a real literature base.
Ported from OpenDraft (github.com/federicodeponte/opendraft, MIT), which runs this
as a hosted engine. Here the engine is you: eighteen stages and one evidence
stage, each a prompt in agents/, plus the scripts that do the parts a language
model must not do by hand.
You are the model. No key, no service, no account. The only network calls are Crossref, OpenAlex and DataCite, all open endpoints.
The one command
Write a paper on <topic>
Everything below follows from that. Do not ask the user to run the stages themselves; run them.
Ask four things first
Before stage 5, if the user has not already said, ask for:
- Target venue, or "none, general academic".
- Total word limit.
- Citation style, one of the six in
references/citation-styles.md. - Document type, one of the types in
references/paper-types.md.
These are four questions in one message, not an interview, and they are the only questions the pipeline asks. Everything else it decides.
Ask because the cost of guessing lands at the end and cannot be paid there. A venue with a hard 150-word abstract cap is enforced at stage 6 or nowhere: by the time stage 17 writes the abstract, the word budget every section was drafted against is already wrong. A citation style chosen at the gate rather than at stage 6 means the whole draft was written against the wrong marker density.
If the user declines to answer, or says "you pick", proceed on the defaults in
references/paper-types.md, write them into the venue format block at stage 6,
and say in one line which defaults you used. Never proceed on an unstated
assumption you did not show them.
Write down the brief's own numbers, then check against them
Most briefs arrive with numbers already in them, in ordinary words: "about 3,000 words", "1200-1500 words", "a couple of dozen sources at least", "caps the main text at 6,000 words and the abstract at 200", "thirty or more works", "cover the hospital series, the exposure problem and the policy evaluations". Each of those is a requirement, and each of them is a requirement this pipeline loses if nobody writes it down, because every stage after the first works from an outline rather than from the request.
What ships with it
58 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.
- .gitignore 34 B
- agents/01-scout.md 20 KB
- agents/02-scribe.md 8.5 KB
- agents/03-signal.md 8.3 KB
- agents/04-citation-manager.md 21 KB
- agents/04.5-evidence.md 6.4 KB
- agents/05-architect.md 17 KB
- agents/06-formatter.md 21 KB
- agents/07-crafter.md 35 KB
- agents/08-thread.md 15 KB
- agents/09-narrator.md 7.6 KB
- agents/10-skeptic.md 11 KB
- agents/11-verifier.md 13 KB
- agents/12-referee.md 8.2 KB
- agents/13-voice.md 13 KB
- agents/14-entropy.md 13 KB
- agents/15-polish.md 13 KB
- agents/16-enhancer.md 22 KB
- agents/17-abstract.md 14 KB
- agents/18-titlemaker.md 15 KB
- assets/equation-1.svg 3.5 KB
- assets/equation-2.svg 4.8 KB
- assets/equation-3.svg 5.7 KB
- assets/fonts/OFL-Source-Sans-3.txt 4.4 KB
- assets/fonts/OFL-STIX-Two.txt 4.4 KB
- assets/fonts/SS-400.ttf 371 KB
- assets/fonts/SS-600.ttf 371 KB
- assets/fonts/SS-700.ttf 371 KB
- assets/fonts/SSi-400.ttf 235 KB
- assets/fonts/STIX-400.ttf 293 KB
- assets/fonts/STIX-600.ttf 293 KB
- assets/fonts/STIX-700.ttf 293 KB
- assets/fonts/STIXi-400.ttf 319 KB
- assets/fonts/STIXi-600.ttf 319 KB
- DERIVATION.json 23 KB
- EVALS.md 29 KB
- LICENSE 11 KB
- references/citation-styles.md 19 KB
- references/paper-types.md 14 KB
- scripts/assemble.py 6.6 KB runs code
- scripts/citations.py 31 KB runs code
- scripts/evidence.py 34 KB runs code
- scripts/export.py 26 KB runs code
- scripts/integrity.py 62 KB runs code
- scripts/journal.py 18 KB runs code
- scripts/sources.py 19 KB runs code
- tests/test_agent_contract.py 16 KB runs code
- tests/test_assemble.py 11 KB runs code
- tests/test_citations.py 25 KB runs code
- tests/test_docs_consistency.py 30 KB runs code
- tests/test_documented_commands.py 8.8 KB runs code
- tests/test_evidence.py 13 KB runs code
- tests/test_export.py 11 KB runs code
- tests/test_integrity.py 68 KB runs code
- tests/test_journal.py 7.3 KB runs code
- tests/test_roundtrip.py 6.2 KB runs code
- tests/test_sources.py 22 KB runs code
- THIRD_PARTY_NOTICES.md 2.4 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.
- 15d ago First seen · 614 lines · 144 tokens per session scan A 56f886f221c9
autonomous-research is a skill published in the GitHub repository federicodeponte/opendraft (512 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 7,850 once invoked, about $0.0006 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 2026-10-02.
Other skills, from other repositories
python-pipeline
Python data pipelines with modular architecture. Use for content workflows, batch jobs, or Google Sheets/Drive integration.
academic-integrity-rewrite
A writing tool for revising Chinese or English academic text while keeping its meaning, evidence, numbers, equations, technical terms, and citations intact. It is intended to reduce unnecessary text overlap in papers, theses, and other research writing.
humanizer-paper
An academic writing editor for English journal articles and Chinese doctoral dissertations. It adjusts wording to fit each type of academic writing.
proposal-supervise
Supervisor-side feedback on a raw student submission — normalize it into the standard proposal format, find the pressing issues via the shared check and review rules, and draft paste-ready feedback. Use when a professor receives a thesis proposal or idea from a student and wants constructive, high-level feedback to…
proposal-write
Write a thesis proposal from scratch or refine one, grounded in the proposal guidelines and the literature. Use when the user wants a draft, wants sections improved, wants bullet points turned into prose, asks to apply review findings or blockers, wants open TODOs moved to the notes file, or asks for a writing…
proposal-check
Low-level check of a thesis proposal — required sections, citation consistency, forbidden content, format guardrails, typos — closing with where it stands and the next step. Use when the user asks to check their proposal, suspects a section or citation is missing or malformed, wants a quick gate before publishing, or…