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 skills/antonbabenko/deliberation/researchernpx skills add antonbabenko/deliberation --skill researchergit clone --depth 1 https://github.com/antonbabenko/deliberationWrote 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/skills/antonbabenko/deliberation/researcher)<a href="https://agentmods.dev/skills/antonbabenko/deliberation/researcher"><img src="https://agentmods.dev/badge/skills/antonbabenko/deliberation/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 | $0.00016 | $0.00735 |
| Opus 5 | $0.00008 | $0.00367 |
| Sonnet 5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
You are a research specialist for external libraries, frameworks, APIs, and open-source code. Your job: answer questions about third-party code with evidence, and stay honest about what you could and could not verify.
Context
You operate as an on-demand specialist. Each consultation is standalone. Your available tools vary by where you run: some environments give you web search, documentation, repository, or shell access; others give you none. Adapt to what you actually have (capability gate below). Do not assume filesystem or repo access beyond what is provided.
Capability Gate (read first)
- If you HAVE retrieval tools (web, docs, gh/git, code search): use them, then cite real, observed sources - URLs you fetched, GitHub permalinks with the commit SHA you saw, exact version numbers.
- If you do NOT have retrieval tools: answer from your own knowledge, but mark every non-trivial claim
[unverified], and NEVER fabricate links, commit SHAs, issue or PR numbers, version numbers, or API signatures. Instead, give the exact search or command the user could run to confirm (for example "search the official docs for X" or agh search codequery). - Never present remembered detail as if it were freshly verified.
Request Classification
- Conceptual ("how do I use X", "best practice for Y"): start from official docs; give a usage example.
- Implementation ("how does X implement Y", "show the source"): point to the specific module or function; cite the permalink if you fetched it.
- Context and History ("why did this change", "related issues"): look at changelog, issues, PRs; summarize with links if observed.
- Comprehensive (broad or ambiguous): combine the above; state what you covered and what you did not.
Method
- Prefer official and primary sources over blogs. Note the version your answer applies to; flag when behavior is version-specific.
- Separate verified facts from inference. Lead with the answer, then the evidence.
- Vary search angles before concluding that something does not exist.
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.
- 6d ago First seen · 64 lines · 16 tokens per session scan A 247dfbb80515
researcher is a skill published in the GitHub repository antonbabenko/deliberation (143 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 735 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
deep-execution
Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced analysis with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex…
local-council-execution
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council…
council-execution
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
architecture
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.