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/learngit 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 | $0.00027 | $0.02096 |
| Opus 5 | $0.00014 | $0.01048 |
| Sonnet 5 | $0.00005 | $0.00419 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade C, and why
autoresearch:learn scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **Secrets (2-layer):** (1) prompt instructs "summarize config, never include verbatim values from .env/credentials or strings matching key/secret/token/password; extract env var *names* not *values*"; (2) post-gen, `gr Copies of this mod
1 near-identical copy found in the catalogue:
- autoresearch_learn — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE IMMEDIATELY.
Parse Arguments
Extract from $ARGUMENTS:
Mode:or--mode— init (create from scratch), update (refresh existing), check (validate), summarize (brief overview), wiki (navigable knowledge base)Scope:or--scope— file globs to documentDepth:or--depth— overview, standard, comprehensive--file <path>— specific file to document--scan— force fresh codebase scout--topics— comma-separated focus topics--modules <list>— wiki mode: comma-separated module names/paths overriding auto-detection--force— wiki mode: regenerate all pages from scratch, ignore existing manifest--no-fix— validate only, don't auto-fix issues--format— markdown (default), json, rstIterations:or--iterations— default 10. "unlimited" for unbounded.--evals,--evals-interval N,--chain,--<subcommand>
Setup (if Mode or Scope missing)
AskUserQuestion (single batch): Q1 (Mode): "What to do?" — init (generate docs), update (refresh), check (validate), summarize (overview), wiki (knowledge base) Q2 (Scope): "Which files?" — suggested globs + entire codebase Q3 (Depth): "How detailed?" — overview only, standard, comprehensive Q4 (Topics): "Focus on?" — architecture, API, database, testing, all If all provided → skip.
Establish Baseline
- Scout codebase: file tree, imports/exports, existing docs
- Identify documentation gaps (undocumented files, outdated docs, missing READMEs)
- Create output directory:
autoresearch/learn-{YYMMDD}-{HHMM}/ - TSV header:
# metric_direction: higher_is_better\niteration\ttimestamp\tfile_documented\tvalidation_status\tissues_found\tissues_fixed\tdescription - Metric = files with valid documentation (higher is better)
Summarize Mode (no loop)
If mode == summarize:
- One-shot: scan codebase → produce structured summary
- Write summary.md to output directory
- Skip iteration loop entirely
Wiki Mode (no per-file loop)
If mode == wiki: reuse Scout (Phase 1) + Analyze output, then generate a navigable wiki/ knowledge base. Skip the init/update/check loop. Metric = pages_generated / pages_planned × 100 (from manifest); size target 300 lines/page.
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 · 137 lines · 27 tokens per session scan C c3d730cabd25
autoresearch:learn is a command published in the GitHub repository uditgoenka/autoresearch (5,966 stars, last pushed 19d ago), licensed MIT. It adds 27 tokens to every session and 2,096 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). 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.
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.