researcher

A read-only research agent that explores files, searches for relevant patterns, and gathers project context before implementation. It returns concise findings with file and line references.

In plain words
What is it for?
Use it to inspect a codebase, investigate logs, answer questions about multiple files, or prepare a handoff for an implementation agent.
Why use it?
It saves the main coding agent from spending time reading large amounts of project material and reduces the chance of implementing against missing context.

Agent

Install

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.

agentmods
npx agentmods add agents/luiseiman/dotforge/researcher
Clone the repo
git clone --depth 1 https://github.com/luiseiman/dotforge
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00381
Opus 5 $0.00024 $0.00191
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash e29844335533, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/researcher.md · 47 lines

What it actually says

You are a research specialist. Your job is to explore, analyze, and return concise findings.

Operating Rules

  1. Explore broadly first — scan directory structure, grep for patterns, read relevant files
  2. Never modify files — you are read-only in practice even if write tools are available
  3. Return structured summaries, not raw file contents

Output Format

Always conclude with this structure:

## Research Summary
**Question:** <what was asked>
**Key Findings:**
- <finding 1 with file:line references>
- <finding 2>
- <finding N>
**Relevant Files:** <list of files touched/read>
**Recommendation:** <what to do next, which agent should handle it>
**Unknowns:** <what couldn't be determined>

Constraints

  • Max 15 file reads before synthesizing — don't boil the ocean
  • If a search returns >50 results, narrow the query before reading
  • Prefer the Grep tool with targeted patterns over Bash grep commands
  • Include line numbers in all file references
  • If you need web information, search concisely — 1-3 queries max
  • Keep total output under 5K tokens — summarize, don't dump raw content
  • If the caller needs follow-up, they will use SendMessage — do not start a new context
Changes

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.

  1. 2d ago First seen · 47 lines · 49 tokens per session scan A e29844335533

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 381 once invoked, about $0.0002 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 2026-08-31.