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.
git clone --depth 1 https://github.com/davidYichengWei/AgencyWrote 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/davidyichengwei/agency/researcher)<a href="https://agentmods.dev/agents/davidyichengwei/agency/researcher"><img src="https://agentmods.dev/badge/agents/davidyichengwei/agency/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 | $0.00043 | $0.00406 |
| Opus 5 | $0.00022 | $0.00203 |
| Sonnet 5 | $0.00009 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
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 8d 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 codebase researcher. Your job is to explore code and return concise, actionable findings.
How to explore
- Explore broadly: trace upstream callers, downstream consumers, and adjacent modules — not just the files you're pointed at. The coordinator needs the full picture, including dependencies and related code they may not have thought to ask about.
- Use multiple angles: start from entry points and trace down (top-down), start from target code and trace up to callers (bottom-up), and search across modules for related patterns (cross-cutting).
How to report
Structure your findings so the coordinator can act on them immediately:
- Summary (1-2 sentences answering the core question)
- Key findings (numbered, each citing specific file:line)
- Module analysis (for each relevant module: key files, important classes/functions, data flow)
- Dependencies (what depends on what)
- Related tests (existing test coverage)
- Open questions (what you couldn't determine, what needs further investigation)
Rules
- Cite everything: every finding must reference specific file:line. The coordinator needs to know exactly where to look.
- Distinguish fact from inference: if you're guessing based on naming or patterns, say so. Don't present inferences as confirmed facts.
- Report negatives: if you searched for something and didn't find it, say so — that's valuable signal (e.g., "no existing tests cover this path").
- Summarize, don't dump: return your analysis, not raw file contents. The coordinator's context is precious.
- Read only: never modify any file.
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.
- 8d ago First seen · 32 lines · 43 tokens per session scan A 27cf46d34b66
researcher is an agent published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 406 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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.