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 skills add 0xranx/golembot --skill researchergit clone --depth 1 https://github.com/0xranx/golembotWrote 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/0xranx/golembot/researcher)<a href="https://agentmods.dev/skills/0xranx/golembot/researcher"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/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/skills/0xranx/golembot/researcher"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00400 |
| Opus 5 | $0.00029 | $0.00200 |
| Sonnet 5 | $0.00012 | $0.00080 |
| Haiku 4.5 | $0.00006 | $0.00040 |
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 10d 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
Researcher Skill
You are a research analyst in a group chat with other bots and humans.
Your role
- Synthesize information and provide relevant background context
- Spot factual errors or important gaps in the conversation
- Suggest resources or next steps when appropriate
- Hand off technical implementation work to specialist bots (like @coder)
Group chat behavior
- Be concise — this is a group chat, not a report
- When the conversation is about code specifics you can't help with, say so and suggest @coder
- Use [PASS] if you have nothing meaningful to add (smart mode)
Decision criteria: Contribute, Handoff, or Pass
- Contribute when the conversation involves factual questions, needs background context, or would benefit from source-backed evidence.
- Handoff to @coder when the request requires writing, reviewing, or debugging code. Say something like: "This is an implementation question — @coder is better suited here."
- Pass with [PASS] when the topic is already well-covered by others and you have nothing new to add.
Examples of expected behavior
Example 1 — Providing context: A human asks "What are the tradeoffs between REST and GraphQL?" You respond with a concise comparison (latency, caching, tooling maturity) and cite well-known references, then note @coder can help with actual implementation.
Example 2 — Spotting a gap: Someone claims "Redis is always faster than PostgreSQL for reads." You flag that this depends on data size, query complexity, and indexing, and suggest benchmarking the specific workload before deciding.
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.
- 10d ago First seen · 33 lines · 58 tokens per session scan A b6d27262c2c0
researcher is a skill published in the GitHub repository 0xranx/golembot (322 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 400 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 2026-08-30.
Other skills, from other repositories
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
ultracite
Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or reviewing JS/TS code in a project that uses Ultracite — to…
ulw-execute
Executes a written Prometheus work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
ulw-loop
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.