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.
Borrowing it
Nothing to install: this file belongs to uditgoenka/autoresearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/uditgoenka/autoresearch/master/.opencode/commands/autoresearch_fix.mdgit 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/autoresearch_fix)<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/autoresearch_fix"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/autoresearch_fix/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/commands/uditgoenka/autoresearch/autoresearch_fix"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/autoresearch_fix.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 | $0.00021 | $0.01144 |
| Opus 5.5 | $0.00008 | $0.00458 |
| Sonnet 5.5 | $0.00004 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
autoresearch_fix 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 1mo 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.
This is a copy
97% identical to autoresearch:fix — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE IMMEDIATELY.
Parse Arguments
Extract from $ARGUMENTS:
Target:or--target— command that shows errors (e.g.,npm test,tsc --noEmit)Scope:or--scope— file globs to modifyGuard:or--guard— safety command (must always pass)Iterations:or--iterations— default 20. "unlimited" for unbounded.--from-debug— read handoff.json from previous debug run--category— filter: test, type, lint, build--evals,--evals-interval N,--chain
Setup (if required context missing)
If Target and Scope both missing:
- Auto-detect failures: run test suite, type checker, linter, build
- Present results via question (single batched call): Q1 (Fix What): "Found [N] test failures, [M] type errors, [K] lint errors. Fix what?" — everything, only tests, only types, only lint Q2 (Guard): "Safety command that must always pass?" — npm test, tsc, npm run build, skip Q3 (Scope): "Which files can I modify?" — suggested globs from error locations + all Q4 (Launch): "Ready?" — fix until zero, fix with limit, cancel If all provided → skip setup. If --from-debug → read handoff.json for scope and findings.
Precondition Checks
Verify: git repo exists, clean working tree, no lock files, no detached HEAD. Fail fast on critical issues.
Establish Baseline (Iteration 0)
- Run Target command → count errors (metric = error count, direction = lower_is_better)
- Record baseline in TSV
- Create output directory:
autoresearch/fix-{YYMMDD}-{HHMM}/ - TSV header:
# metric_direction: lower_is_better\niteration\ttimestamp\terror_type\terror_fixed\tcommit\tmetric\tdelta\tguard\tstatus\tdescription
Iteration Loop (until zero errors or max_iterations)
Phase 1: Review
- Read results TSV + git log
- Run Target to get current error list
- If error count == 0 → exit loop (SUCCESS)
Phase 2: Prioritize
Order: crash/fatal → test failures → type errors → lint → warnings. Within category: easiest first (single-file fixes before cross-file).
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.
- 1mo ago First seen · 103 lines · 21 tokens per session scan A cfc4ede737dd
autoresearch_fix is a command published in the GitHub repository uditgoenka/autoresearch (6,763 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,144 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to autoresearch:fix, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
timeout-fix
A procedure for diagnosing and fixing tests that exceed their time limit by finding causes such as slow processing, hanging network calls, deadlocks, heavy setup, or leaked resources.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.