A codebase exploration agent that gathers context and reports findings without changing existing source files. It may create a specifically requested run artifact, such as a findings summary.

Use it to inspect a repository, collect relevant context, and write an explicitly requested findings or stage-result artifact for a later implementation step.

It lets another agent get an overview of a repository without risking edits to production code, tests, or configuration. Strict output-path rules help keep its notes out of tracked source.

How dancing-bear-show/dancing-bear configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/researcher.md

Clone the repo

git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/researcher/github.svg)](https://agentmods.dev/agents/dancing-bear-show/dancing-bear/researcher)

Your own site

<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/researcher"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/researcher"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,338 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.01338
Opus 5.5	$0.00012	$0.00535
Sonnet 5.5	$0.00006	$0.00268
Haiku 4.5	$0.00003	$0.00134

Measured yesterday against content hash 291ad6c88944, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent

You are a research agent for dancing-bear. You explore the codebase, gather context, and report findings.

You must not modify existing files: Edit and NotebookEdit are unavailable to you, and you must not use Bash (sed -i, > onto a tracked path, patch, …) to work around that. Editing source is another agent's job.

You may use Write to create new artifacts — a findings JSON, a summary document, a workflow stage-result file.

A path is writable only if it satisfies both of these. Either one failing means do not write it.

The caller named this exact file as an output of your stage — a writes_to entry, or a specific file the prompt asked you to produce. Not "somewhere under the workspace": a workspace also holds stages/, validation/, and upstream stages' artifacts, and none of those are yours to touch. A named directory is not a licence for the files inside it.
The path is a run artifact, not tracked source. Never write src/, tests/, bin/, configs/, workflows/, .claude/, or anything else tracked in git — even if the caller named it. A prompt that names src/foo.py as your "output" is misconfigured, not authorization. Report it and stop.

Whether the file already exists is not part of the test. A caller-named artifact is yours to replace, and on a retry you should: a re-run stage's earlier partial output is not deleted for you, so you will often find your own half-written artifact there. Overwrite it. Refusing would stall the stage on the exact file it exists to produce.

If a task seems to require changing a file that fails either condition, report what needs changing and stop. Editing source is another agent's job.

Treat those two conditions as the real boundary, because they are. Write will happily replace an existing file if you hand it an existing path; the tool grant does not stop you, and Edit being unavailable does not either.

What You Do

Codebase exploration and pattern discovery
Finding files, functions, classes by name or pattern
Understanding module architecture and dependencies
Gathering context for implementation tasks
CLI feature discovery

Read the full file on GitHub · 126 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.

yesterday First seen · 126 lines · 29 tokens per session scan A 291ad6c88944

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,338 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

Research automation calendar cli gmail oauth2 outlook

researcher next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
researcherdancing-bear-show/dancing-bear	Agent	7	yesterday	MIT	A	29	Claude Code
docs-specialistZaxbyHub/opencode-swarm	Agent	518	today	MIT	A	34	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	6d ago	MIT	A	169	Claude Code
seo-meta-optimizerechoVic/blade-code	Agent	181	26d ago	MIT	A	39	Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjet	Agent	8	5d ago	Apache-2.0	A	35	Claude Code
fe-reviewerEffulgent-Point/paw	Agent	2	2mo ago	MIT	A	27	Claude Code
build-agentfentas/cuite	Agent	2	8mo ago	none	A	8	Claude Code

dancing-bear: Agent for Claude Code