Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zjunlp/Mechanistnpx agentmods add skills/zjunlp/mechanist/auto-claimWrote 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/zjunlp/mechanist/auto-claim)<a href="https://agentmods.dev/skills/zjunlp/mechanist/auto-claim"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/auto-claim.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 88 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 648 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00298 | $0.14914 |
| Opus 5 | $0.00149 | $0.07457 |
| Sonnet 5 | $0.00060 | $0.02983 |
| Haiku 4.5 | $0.00030 | $0.01491 |
Grade A, and why
auto-claim 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 — 671 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow 1: Claim Stage — Behavior (given / given-validation / discovery) × Mechanism (given / discovery)
Orchestrate the claim stage for: $ARGUMENTS. Two orthogonal constants drive everything: BEHAVIOR_SOURCE (where the behavior comes from + whether it is validated) and MECHANISM (who picks the mechanism method).
Overview
This skill chains sub-skills into a single automated pipeline. All combinations share Phases 0, 0.5, 1, 4.5, 5, and 5.5; they differ in how the claim(s) entering Phase 4.5 are produced (Phase 2 + the ideation Phases 3/3.5/4) and in what Phase 1.75 loads.
Behavior stage — BEHAVIOR_SOURCE decides the behavior origin, whether ideation runs, and whether the plan opens with an M0 phenomenon-validation gate:
given(default) — the behavior is already specified in the direction /task.mdand assumed to hold. Faithfully capture it (no ideation, no novelty, no M0) and go straight to the mechanism:/research-lit → faithful behavior capture (from task.md) → /research-refine-pipelinegiven-validation— the behavior is captured the same way (no mining, no ideation, no novelty) but its existence is validated first: the experiment plan opens with a hard M0 gate that the experiment stage runs before any mechanism compute./research-lit → faithful behavior capture (from task.md) → /research-refine-pipeline (plan opens with M0)discovery— the behavior itself is mined:/mechanism-behavior-discoverysharpens a new candidate phenomenon, then full ideation generates and ranks mechanistic ideas; the plan opens with the M0 gate too.
The final idea is selected by combined impact + novelty, with impact weighted first (a less-novel idea on an important problem outranks a novel idea nobody needs)./research-lit → /idea-creator → /novelty-check → /impact-check → /research-review → /research-refine-pipeline (survey) (brainstorm) (verify novel) (verify it (critical feedback) (refine method + plan) matters)
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 · 671 lines · 298 tokens per session scan A f5aa00bbc0a6
auto-claim is a skill published in the GitHub repository zjunlp/Mechanist (72 stars, last pushed 12d ago), licensed MIT. It adds 298 tokens to every session and 14,914 once invoked, about $0.0015 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
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
nanoresearch-planning
Produce an experiment blueprint from a research hypothesis.
nanoresearch-ideation
Search academic literature and generate research hypotheses.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.