autoresearch is an agent workflow that repeatedly changes a project, verifies a measurable result, keeps or discards the change, and continues iterating toward a goal. It is for autonomous improvement tasks in Claude Code, OpenCode, and OpenAI Codex across domains with mechanical success measures. The catalogue contains its commands, hooks, skills, plugin, agent, and instruction.
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 commands/uditgoenka/autoresearch/reasongit clone --depth 1 https://github.com/uditgoenka/autoresearchWrote 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/commands/uditgoenka/autoresearch/reason)<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/reason"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/reason.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 | $0.00014 | $0.01205 |
| Opus 5 | $0.00007 | $0.00602 |
| Sonnet 5 | $0.00003 | $0.00241 |
| Haiku 4.5 | $0.00001 | $0.00120 |
Grade A, and why
autoresearch:reason 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- autoresearch_reason — 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE IMMEDIATELY.
Parse Arguments
Extract from $ARGUMENTS:
Task:— question, proposal, design, argument, or claim to refineDomain:or--domain— software, product, business, security, research, contentMode:or--mode— convergent (default), creative, debate--judges NorJudges:— blind judge count (3 default, 5 thorough, 7 deep)--convergence NorConvergence:— stop when incumbent wins N consecutive rounds (default 3)Iterations:or--iterations— default 8. "unlimited" for unbounded.--judge-personas— custom judge persona overrides--no-synthesis— skip synthesis, pure debate only--temperature— generation temperature hint--evals,--evals-interval N,--chain,--<subcommand>
Remaining text not matching flags = task description.
Setup (if Task or Domain missing)
AskUserQuestion (single batch): Q1 (Task): "What should be reasoned about?" — open text Q2 (Domain): "What domain?" — software architecture, product strategy, business decision, security, research, content Q3 (Mode): "Refinement mode?" — convergent (stop when winner repeats), creative (never auto-stop), debate (no synthesis) Q4 (Judges): "How many blind judges?" — 3 (default), 5 (thorough), 7 (deep) If all provided → skip.
Setup Phase
- Load
references/reason-judge-protocol.mdfor judge and convergence specs - Parse domain → select domain-specific judge criteria
- Create output directory:
autoresearch/reason-{YYMMDD}-{HHMM}/ - TSV header:
round\ttimestamp\tcandidate_label\tjudge_verdict\tconvergence_count\tdescription - Initialize: incumbent = null, convergence_count = 0
Round Loop
Phase 1: Generate-A
- If round 1: Author-A generates first candidate from task description
- If round N>1: incumbent is Author-A's candidate
- Cold-start: Author-A sees ONLY task description + domain context
Phase 2: Critic
- Critic receives candidate-A (cold-start, no shared session)
- MUST find at least 3 specific weaknesses
- MUST suggest what a superior candidate would do differently
- Role is purely adversarial — never compliment
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 · 110 lines · 14 tokens per session scan A 243492e7f7ff
autoresearch:reason is a command published in the GitHub repository uditgoenka/autoresearch (6,116 stars, last pushed 23d ago), licensed MIT. It adds 14 tokens to every session and 1,205 once invoked, about $0.0001 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 commands, from other repositories
drift
Read the Genesis build phases document: docs/architecture/genesis-v3-build-phases.md.
challenge
Read the specified design doc section.
thoth:dashboard
Alias for status --dashboard; manage the local dashboard backed by .thoth ledgers.
run-autoresearch
Run an autonomous experiment loop via the Autoresearch Orchestrator agent.
onboard
/anty:onboard — QUEST-Based Conversational Interview.
next-issue
Fetch the next ready-for-agent issue by priority.