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/autoresearch_fixgit clone --depth 1 https://github.com/uditgoenka/autoresearchWhat 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 | $0.00021 | $0.01144 |
| Opus 5 | $0.00010 | $0.00572 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 103 lines · 21 tokens per session scan A cfc4ede737dd
autoresearch_fix is a command published in the GitHub repository uditgoenka/autoresearch (5,966 stars, last pushed 19d ago), licensed MIT. It adds 21 tokens to every session and 1,144 once invoked, about $0.0001 per session on Opus 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
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.
thoth:doctor
Alias for status --doctor; strictly audit project health without writing authority.
feature
End-to-end feature/bug-sweep workflow for aitm — understand, reproduce against a real run, explore and build with a hive of parallel agents in this one checkout (never worktrees), path-disjoint slices, verify under Bun AND Node, PR, merge, and (only when asked) release to npm. Tracks in GitHub issues. Reads intent…
merge-pr
Drive an open PR to merge, then advance to the next PR group.