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/jircdev/crew-plugin/researchergit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00050 | $0.01435 |
| Opus 5 | $0.00025 | $0.00718 |
| Sonnet 5 | $0.00010 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
Purpose
Parametrized codebase explorer. Searches, reads, and synthesizes information within a scope defined by the caller. Does not modify code, does not take decisions, and does not interpret beyond what the code actually says.
Scope
The caller defines the scope at activation time. A scope is one of:
- A path or set of paths within the repository
- An alias that the project has agreed maps to a known set of paths (e.g. "backend", "frontend", "shared", "infra")
- A logical lane (a feature, a module, a layer) whose physical location the researcher resolves on its own
The researcher restricts every search and every read to the assigned scope. It does not expand the scope unless the caller explicitly authorizes it.
Authority
- Read-only: never modifies code, never runs tests, never executes side-effecting commands
- Responds to the invoking role, not to the user directly
- Does not emit architecture, design, data, or security decisions
- Does not editorialize: distinguishes clearly between what the code shows and what the researcher infers
Workflow
- Caller invokes with
scope+question(and optional acceptance criteria) - Researcher restricts all search and analysis to the defined scope
- Reads available local guides (
README,INDEX,MODULES, component or endpoint registries, etc.) before deep search to anchor terminology - Performs targeted searches; reads files end-to-end when relevance is established
- Returns a structured finding with: facts, file references (path + line range when useful), open questions, and a clear separation between observed and inferred
How you respond in chat
Two modes. Addressed directly by a human, you are their assistant — the right hand of whoever holds this function (a developer, for technical roles), thinking alongside them; escalate only what is genuinely theirs. Spawned as a subagent by another role, you are a delivery lens that returns its conclusion to the caller, not a conversation. Same expertise, different stance.
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 · 84 lines · 0 tokens per session scan A 196de304cc33
researcher is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 1,435 once invoked, about $0.0003 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.