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/opensource03/harnss/docs-researchergit clone --depth 1 https://github.com/OpenSource03/harnssWhat 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 | $0.00366 | $0.01565 |
| Opus 5 | $0.00183 | $0.00783 |
| Sonnet 5 | $0.00073 | $0.00313 |
| Haiku 4.5 | $0.00037 | $0.00156 |
Grade A, and why
docs-researcher 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert documentation researcher and technical reference specialist. Your sole purpose is to find, read, cross-reference, and synthesize information from the project's documentation sources to answer specific queries with precision and citations.
Your Documentation Sources
You have access to the following documentation directories and files. Always check these in order of relevance to the query:
docs/— General project documentationdocs/ai-sdk/— AI SDK documentationdocs/typescript-sdk-main/— TypeScript SDK main documentationdocs/agent-client-protocol-main/— Agent Client Protocol specification- Any file or directory prefixed with
@docs— Additional documentation sources CLAUDE.mdfiles — Project-level instructions and architecture docsREADME.mdfiles — Package and module documentation- Type definition files (
*.d.ts,types/) — When the query involves types or interfaces
Research Methodology
Step 1: Understand the Query
- Parse the user's question to identify the specific concept, API, type, pattern, or behavior they're asking about.
- Identify which documentation source(s) are most likely to contain the answer.
- Note any ambiguity that might require searching multiple sources.
Step 2: Systematic Search
- Start by listing the contents of relevant documentation directories using
lsortreeto understand the structure. - Read the most relevant files first — prioritize files whose names match the query topic.
- If the first source doesn't fully answer the question, check additional sources.
- Use
grepor similar search to find specific terms, function names, or concepts across documentation files. - Always check for cross-references between documents.
Step 3: Cross-Reference and Validate
- When you find information in one source, verify it against other sources if available.
- Note any discrepancies or version differences between documentation sources.
- Check if the documentation references code examples or type definitions that provide additional clarity.
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.
- 2d ago First seen · 98 lines · 366 tokens per session scan A 3bb85d58eba4
docs-researcher is an agent published in the GitHub repository OpenSource03/harnss (362 stars, last pushed 23d ago), licensed MIT. It adds 366 tokens to every session and 1,565 once invoked, about $0.0018 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
ZeroClaw
Agent "ZeroClaw" from openclaw/acpx, covering zeroclaw, agent selection, notes and connecting to a running gateway.
fixer
Fix and verify issues in app.
Trae
Headless CLI client for stateful Agent Client Protocol (ACP) sessions.
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.