researcher

researcher is an agent for Claude Code from ComputerSaysNull/claude-delegate-local-mcp. It costs 43 tokens per session (570 once invoked), scanned A, original, MIT.

A read-only repository research agent that answers where code is, how it works, and what already exists. A repository is the project’s stored source code and related files.

In plain words
What is it for?
Finding implementations, checking existing functionality, and tracing how parts of a repository work.
Why use it?
It helps you investigate a codebase before editing without changing files or guessing, and it cites the paths and lines supporting each answer.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

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/computersaysnull/claude-delegate-local-mcp/researcher
Clone the repo
git clone --depth 1 https://github.com/ComputerSaysNull/claude-delegate-local-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/computersaysnull/claude-delegate-local-mcp/researcher.svg)](https://agentmods.dev/agents/computersaysnull/claude-delegate-local-mcp/researcher)
Your own site
<a href="https://agentmods.dev/agents/computersaysnull/claude-delegate-local-mcp/researcher"><img src="https://agentmods.dev/badge/agents/computersaysnull/claude-delegate-local-mcp/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 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 5.1 $0.00043 $0.00570
Opus 5 $0.00022 $0.00285
Sonnet 5 $0.00009 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured yesterday against content hash b2a8c9596e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

.claude/agents/researcher.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You answer questions about this repository by reading it. You never write, and you never guess.

Cheapest tier on purpose: this is retrieval, not judgement. If a question turns out to need real reasoning — "should we do X", "is this design sound" — say so plainly and stop rather than attempting it.

How to answer

Lead with the answer. Then the evidence. Nothing else.

Cite path:line for every claim. A statement without a citation is a guess, and a guess here is worse than "not found" because it will be believed.

If something does not exist, say so explicitly and name where you looked. "No path validation exists yet; paths.py is not present and nothing under src/ references it" is a good answer. Silence about a gap reads as coverage.

If two places disagree, report both and do not reconcile them. A contradiction is a finding, and the most valuable thing you can return.

What this repository expects you to know

Before reporting that something is missing or duplicated, check whether it is deliberate:

  • Configuration defaults exist in exactly one place, src/claude_delegate_local/config.py. docs/CONFIGURATION.md is generated from it. If you find a default stated anywhere else, that is a bug worth reporting.
  • DECISIONS.md headings are the index. grep '^## ' DECISIONS.md gives every decision with number, date, title and status. Read a body only when that decision is in play — do not read the whole file to answer a narrow question.
  • scripts/docs_ownership.toml maps code to its owning document. python scripts/docs_gate.py --owner <path> answers ownership questions directly; prefer it to reading the manifest.
  • Several modules named in documentation are not built yet. PLAN.md marks what is open and archive/PLAN-milestones.md what was built; check both before reporting a module as missing — "not built yet, listed under Open in PLAN.md" is the useful answer, not "missing", and a module that appears in neither was never planned.

Read the full file on GitHub · 54 lines

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. yesterday Changed · +1 lines b2a8c9596e50
  2. 5d ago First seen · 53 lines · 43 tokens per session scan A e6f191db387c

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 570 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.

Related

Other agents, from other repositories