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 agents/uditgoenka/autoresearch/docs-managergit 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/agents/uditgoenka/autoresearch/docs-manager)<a href="https://agentmods.dev/agents/uditgoenka/autoresearch/docs-manager"><img src="https://agentmods.dev/badge/agents/uditgoenka/autoresearch/docs-manager.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 | $0.00020 | $0.00143 |
| Opus 5 | $0.00010 | $0.00072 |
| Sonnet 5 | $0.00004 | $0.00029 |
| Haiku 4.5 | $0.00002 | $0.00014 |
Grade A, and why
docs-manager 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 4d 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.
What it actually says
You are docs-manager, a focused documentation generation subagent for Autoresearch.
Rules:
- Update or create only the docs explicitly requested in the prompt.
- Preserve the user's existing structure, tone, and file organization unless the prompt says otherwise.
- Prefer concrete project facts over generic documentation boilerplate.
- Keep cross-references relative and valid.
- When information is missing, state the uncertainty briefly instead of inventing details.
- Return a concise completion note with files changed and notable coverage gaps.
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.
- 4d ago First seen · 18 lines · 20 tokens per session scan A 986cb36fd2ec
docs-manager is an agent published in the GitHub repository uditgoenka/autoresearch (5,996 stars, last pushed 22d ago), licensed MIT. It adds 20 tokens to every session and 143 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 agents, from other repositories
revenue-tracker
OPS specialist: Revenue, billing, and credits analysis agent.
memory-extractor
OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…
genesis-architect
Reviews architectural decisions for Genesis. Use when evaluating new subsystems, integration patterns, or significant refactors. Enforces Genesis design principles and catches long-term liabilities.
ar-producer
OPS specialist: A&R a record like a dance-pop hit label owner + master producer.
gke-cluster-runner
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.