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 queelius/claude-anvil --skill researchgit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/research)<a href="https://agentmods.dev/skills/queelius/claude-anvil/research"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/research/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/queelius/claude-anvil/research"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/research.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 | $0.00051 | $0.00573 |
| Opus 5.5 | $0.00020 | $0.00229 |
| Sonnet 5.5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
research 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Research Agent
Launch an autonomous research agent that iterates toward a goal through proofs, code, simulations, tests, and counterexample search.
Step 1: Parse the Goal
Read the user's message to extract:
- Goal (required): The natural-language research objective. This is the main content of the user's message.
- Eval script (optional): A path to an executable script. Look for phrases like "eval script at", "use ... as eval", or a path ending in
.sh,.py, or similar.
If the goal is unclear, ask the user to clarify before proceeding. If no eval script is mentioned, the agent will self-evaluate.
Step 2: Verify Eval Script (if provided)
If an eval script path was given, verify it exists (Read tool). If it does not exist, tell the user and ask whether to proceed with self-evaluation instead.
Step 3: Check for an Existing Run
If .research/ already exists in this directory (Glob tool), do not launch fresh. Tell the user a prior run lives here and offer: /research-agent:resume to continue it, or archiving it (mv .research .research-archive/<timestamp>) before starting fresh. The agent itself also refuses to clobber goal.md/log.md.
Step 4: Launch the Agent
Spawn the researcher agent (Agent tool, subagent_type: research-agent:researcher) with this prompt structure:
<goal>
{the user's research goal, verbatim}
</goal>
<eval>
{path to eval script, or "none - use self-evaluation"}
</eval>
<working_directory>
{current working directory}
</working_directory>
Begin your research. Create .research/ and start the DECOMPOSE phase.
The agent runs autonomously from here. Inform the user:
Research agent launched. It will work autonomously in this directory, writing progress to
.research/log.md. When it finishes, the synthesis will be at.research/synthesis.md.While it runs, you can:
/research-agent:statusto see cycle progress, current focus, and eval trend (read-only)/research-agent:resumeto continue after an interruption or session restart/research-agent:synthesizeto force conclusion if results are good enough or the agent is stalling
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 · 57 lines · 51 tokens per session scan A e69ba5cf4865
research is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 573 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…
cpp-reinforcement-learning
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…
auto-research
Autonomous research loop that iteratively improves code through experiments. Runs experiments on local or remote GPUs, tracks results, keeps improvements, discards failures, and never stops. TRIGGER THIS SKILL when users want to autonomously research, optimize, or experiment on a problem — whether they say "run…
alphaxiv-paper-lookup
Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.
manim-video
Create mathematical, geometric and scientific videos with Manim Community in Python. Use when animating equations, graphs, transformations or educational explanations; distinguish Manim Community from ManimGL and deliver a rendered, inspected video.
lighting-report-extract
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.