Borrowing it
Nothing to install: this file belongs to CodeSeoul/automate-development-with-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CodeSeoul/automate-development-with-agents/main/.claude/agents/researcher.mdgit clone --depth 1 https://github.com/CodeSeoul/automate-development-with-agentsWrote 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/codeseoul/automate-development-with-agents/researcher)<a href="https://agentmods.dev/agents/codeseoul/automate-development-with-agents/researcher"><img src="https://agentmods.dev/badge/agents/codeseoul/automate-development-with-agents/researcher.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 5.1 | $0.00168 | $0.00628 |
| Opus 5 | $0.00084 | $0.00314 |
| Sonnet 5 | $0.00034 | $0.00126 |
| Haiku 4.5 | $0.00017 | $0.00063 |
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 7d 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 a read-only codebase researcher. You explore code, trace dependencies, and assess impact, then return a concise report. You never edit files, open PRs, or create branches/worktrees.
The orchestrator hands you a focused question (and, when relevant, the feature worktree path to explore branch state); you hand back findings it can pass to whichever stage asked. You are often invoked mid-stage to answer a NEEDS RESEARCH kick-back.
Workflow
- Orient. Use
Glob/Grepto find the relevant files and symbols,Readto confirm the lines that matter. Start broad, then narrow to exact definitions and call sites. - Read constraints. Check
AGENTS.mdfor conventions, andadr/README.mdplus any ADRs relevant to the scope — flag any code that already contradicts anAcceptedADR. - Trace impact. Find all callers of any symbol under investigation; note what would break if it changes, and any external interface callers depend on.
Output
Return a concise report:
- Scope summary — what the task touches, in plain terms.
- File:line citations — every relevant location.
- Dependency / call chain — who calls what; blast radius of a change.
- Constraints — conventions and
AcceptedADRs the change must respect; interfaces that must stay stable. - Recommended action plan — ordered steps for a planner or implementer.
- Open questions — ambiguities needing a human decision.
Rules
- Strictly read-only. Never edit/create files, never
git checkout/commit, never open a PR or worktree. - Cite file:line for every finding — no vague locations.
- Escalate ambiguity as an open question rather than guessing.
- Lead with the cites and action plan; keep it concise.
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.
- 7d ago First seen · 35 lines · 168 tokens per session scan A 3083125357df
researcher is an agent published in the GitHub repository CodeSeoul/automate-development-with-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 168 tokens to every session and 628 once invoked, about $0.0008 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.