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/plangit 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/plan)<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/plan"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/plan.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 | $0.00018 | $0.00735 |
| Opus 5 | $0.00009 | $0.00367 |
| Sonnet 5 | $0.00004 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade C, and why
autoresearch:plan scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. **Safety screen:** check proposed command for rm -rf, fork bombs, curl|sh, credentials Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Safety screen:** check proposed command for rm -rf, fork bombs, curl|sh, credentials Copies of this mod
1 near-identical copy found in the catalogue:
- autoresearch_plan — 91% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 96 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:— text after keyword, or full $ARGUMENTS if no keyword--chain <targets>— comma-separated downstream commands--<subcommand>— chain shorthand
Remaining text = goal description.
Setup (if Goal missing)
AskUserQuestion (single batch): Q1 (Goal): "What do you want to achieve?" — open text Q2 (Type): "What kind of goal?" — improve a metric, fix errors, audit security, explore edge cases, document code, ship something If Goal provided → skip.
Phase 1: Analyze Goal
Parse the goal to determine:
- Is it measurable? (metric-driven vs subjective)
- What's the natural scope? (files, modules, entire codebase)
- What subcommand fits best? (core loop, fix, debug, security, etc.)
Phase 2: Derive Scope
- Scan project structure
- Identify files relevant to the goal
- Propose file globs
- If ambiguous → ask user to confirm
Phase 3: Derive Metric + Direction
For metric-driven goals:
- Identify what to measure (test coverage, error count, bundle size, latency, etc.)
- Determine direction: higher_is_better or lower_is_better
- Propose metric name and description
For subjective goals:
- Suggest proxy metrics where possible
- Or recommend /autoresearch:reason for non-measurable goals
Phase 4: Derive Verify Command
- Identify how to extract the metric as a number from a shell command
- Propose Verify command (e.g.,
npm test -- --coverage | grep "All files" | awk '{print $10}') - Safety screen: check proposed command for rm -rf, fork bombs, curl|sh, credentials
- Dry-run the Verify command → confirm it outputs a valid number
- If dry-run fails → adjust command and retry
Phase 5: Derive Guard (optional)
Propose a Guard command if applicable:
- Test suite:
npm test/pytest/go test ./... - Type check:
tsc --noEmit/mypy - Build:
npm run build - None if not applicable
Phase 6: Suggest Iterations
Based on goal complexity:
- Simple metric improvement → 10-15
- Moderate refactoring → 20-25
- Complex multi-file changes → 30+
- Recommend bounded default, mention
Iterations: unlimitedoption
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 · 96 lines · 18 tokens per session scan C 0386c2b9666c
autoresearch:plan is a command published in the GitHub repository uditgoenka/autoresearch (6,116 stars, last pushed 23d ago), licensed MIT. It adds 18 tokens to every session and 735 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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.