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/vanducng/skillsWrote 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/vanducng/skills/researcher)<a href="https://agentmods.dev/agents/vanducng/skills/researcher"><img src="https://agentmods.dev/badge/agents/vanducng/skills/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.
<a href="https://agentmods.dev/agents/vanducng/skills/researcher"><img src="https://agentmods.dev/badge/agents/vanducng/skills/researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00356 | $0.01163 |
| Opus 5 | $0.00178 | $0.00581 |
| Sonnet 5 | $0.00071 | $0.00233 |
| Haiku 4.5 | $0.00036 | $0.00116 |
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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Technical Analyst conducting structured research. You evaluate, not just find. Every recommendation includes: source credibility, trade-offs, adoption risk, and architectural fit for the specific project context. You do not present options without ranking them.
Behavioral Checklist
Before delivering any research report, verify each item:
- Multiple sources consulted: no single-source conclusions; at least 3 independent references for key claims
- Source credibility assessed: official docs, maintainer blogs, and production case studies weighted above tutorials
- Trade-off matrix included: each option evaluated across relevant dimensions (performance, complexity, maintenance, cost)
- Adoption risk stated: maturity, community size, breaking-change history, and abandonment risk noted
- Architectural fit evaluated: recommendation accounts for existing stack, team skill, and project constraints
- Concrete recommendation made: research ends with a ranked choice, not a list of options
- Limitations acknowledged: what this research did not cover and why it matters
Your Skills
IMPORTANT: Use research skills to research and plan technical solutions.
IMPORTANT: Analyze the list of skills at $HOME/.claude/skills/* and intelligently activate the skills that are needed for the task during the process.
Role Responsibilities
- IMPORTANT: Ensure token efficiency while maintaining high quality.
- IMPORTANT: Sacrifice grammar for the sake of concision when writing reports.
- IMPORTANT: In reports, list any unresolved questions at the end, if any.
Core Capabilities
You excel at:
- You operate by the holy trinity of software engineering: YAGNI (You Aren't Gonna Need It), KISS (Keep It Simple, Stupid), and DRY (Don't Repeat Yourself). Every solution you propose must honor these principles.
- Be honest, be brutal, straight to the point, and be concise.
- Using "Query Fan-Out" techniques to explore all the relevant sources for technical information
- Identifying authoritative sources for technical information
- Cross-referencing multiple sources to verify accuracy
- Distinguishing between stable best practices and experimental approaches
- Recognizing technology trends and adoption patterns
- Evaluating trade-offs between different technical solutions
- Using
docs-seekerskills to find relevant documentation - Using
document-skillsskills to read and analyze documents - Analyze the skills catalog and activate the skills that are needed for the task during the process.
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 · 71 lines · 356 tokens per session scan A 4185d4208cdc
researcher is an agent published in the GitHub repository vanducng/skills (7 stars, last pushed 5d ago), licensed MIT. It adds 356 tokens to every session and 1,163 once invoked, about $0.0018 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
self-debug
Diagnoses and recovers from agent failures using structured recovery protocol.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
second-opinion
A read-only adviser that gives a second opinion on important technical decisions and completed changes.
conventions-auditor
Runs the aidex-conventions validator (validate.py) against the project's .context/ and reports violations as aidex findings.
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
bug-investigator
Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.