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/improvegit 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/improve)<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/improve"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/improve.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 | $0.00016 | $0.01506 |
| Opus 5 | $0.00008 | $0.00753 |
| Sonnet 5 | $0.00003 | $0.00301 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
autoresearch:improve 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_improve — 95% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE IMMEDIATELY.
Parse Arguments
Extract from $ARGUMENTS:
Goal:— product area to improve (or full $ARGUMENTS if no keyword)--icporICP:— ideal customer profile description--discover— force inline codebase scan even when context exists--no-discover— skip auto-discover, warn instead--seeds <categories>— override default research category seeds--depth— shallow (5 iterations), standard (15), deep (30)--features— comma-separated feature names to pre-select for PRD generationIterations:or--iterations— default 15. "unlimited" for unbounded.--evals,--evals-interval N
If upstream handoff.json exists in CWD → read it. Map source findings to default seed categories:
- probe → ICP challenges, UX & experience
- predict → Competitor gaps, Revenue & growth
- debug/security → Competitor gaps, ICP challenges
- Override with
--seeds.
Setup (if Goal or ICP missing)
AskUserQuestion (single batch): Q1 (Goal): "What product area to improve?" — open text Q2 (ICP): "Who is your ideal customer?" — open text describing target buyer/user Q3 (Pain points): "Top 3 pain points your customers face?" — open text Q4 (Competitors): "Key competitors?" — open text, or "skip" Q5 (Depth): "How deep?" — shallow (5 iterations, quick scan), standard (15, recommended), deep (30+, exhaustive) If all provided inline → skip.
Phase 1: Product Context
Resolve product context (priority chain):
- Learn summary (
autoresearch/learn-*/summary.md, most recent) → read it - README.md (≥500 chars, non-boilerplate) → extract product description
package.json/pyproject.toml/Cargo.tomldescription (≥10 chars) → use it- If ALL above absent AND NOT
--no-discover→ auto-discover: scan 10 key files (manifest, routes, models, config), cap 1500 tokens - If
--discover→ force scan regardless of above - If nothing found → warn: "No product context. Run
/autoresearch:learn --mode summarizefor better results."
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 · 117 lines · 16 tokens per session scan A b3711805044d
autoresearch:improve is a command published in the GitHub repository uditgoenka/autoresearch (6,116 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 1,506 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.