swarm: Skill for Claude Code

.skills/claim/SKILL.md

claim is a skill for Claude Code from swarm-ai-research/swarm. It costs 73 tokens per session (1,977 once invoked), scanned A, original, MIT.

A guided tool for creating or updating claim cards in a research vault. A claim card records a proposition, its evidence, confidence, and limits.

In plain words
What is it for?
Use it to create claims, add supporting evidence, change their status, or view claim health.
Why use it?
It gives research claims a consistent record instead of leaving evidence and uncertainty spread across notes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

This is swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.skills/claim/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

Made for: Claude Code.

Wrote 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.

agentmods badge for claim

README.md
[![agentmods](https://agentmods.dev/badge/skills/swarm-ai-research/swarm/claim/github.svg)](https://agentmods.dev/skills/swarm-ai-research/swarm/claim)
Your own site
<a href="https://agentmods.dev/skills/swarm-ai-research/swarm/claim"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/claim/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.

agentmods 80×15 button for claim

Your own site · 80×15
<a href="https://agentmods.dev/skills/swarm-ai-research/swarm/claim"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 9
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01977
Opus 5 $0.00036 $0.00988
Sonnet 5 $0.00015 $0.00395
Haiku 4.5 $0.00007 $0.00198

Measured 7d ago against content hash 9dcf1629d386, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 7d 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.

.skills/claim/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

  • create [proposition] → create a new claim card (Step 1–6)
  • update [claim-id] → update an existing claim (Step 7–9)
  • status → show claim health dashboard (Step 10)
  • list → list all claims with status and confidence (Step 11)
  • Empty → show help with subcommand options

CREATE MODE: Steps 1–6

Step 1: Parse Proposition

The proposition is the claim stated as a testable sentence. It becomes both the filename and the H1 title.

Rules:

  • Must be a complete proposition (not a label or question)
  • Composability test: "This note argues that [proposition]"
  • Lowercase, no trailing period
  • Filename: kebab-case with claim- prefix. E.g., "circuit breakers alone outperform full governance stacks" → claim-circuit-breakers-alone-outperform-full-governance-stacks.md
  • Truncate filename to max 80 chars if needed

If no proposition provided, ask: "State the claim as a testable proposition (e.g., 'transaction tax above 5% reduces welfare')."

Step 2: Gather Evidence

Search for supporting runs:

  1. Ask the user: "Which run(s) support this claim? (run_id or 'search')"
  2. If user says "search":
    • Ask for keywords related to the claim
    • Search run-index.yaml by tags
    • Search runs/*/summary.json for relevant metrics
    • Present top candidates with one-line summaries
  3. For each supporting run, extract:
    • run_id
    • Primary metric and value
    • Effect size (Cohen's d), p-value, correction method, sample size
    • Construct the detail string: "d={d}, p={p}, N={N}, {correction}-corrected"

Step 3: Assess Confidence

Based on the evidence gathered, recommend a confidence level:

Confidence Criteria
high Bonferroni-significant AND replicated across ≥2 independent runs/seeds
medium Nominally significant OR single-sweep support with BH correction
low Suggestive but underpowered (<20 seeds) or unreplicated
contested Conflicting evidence from different runs

Read the full file on GitHub · 218 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 218 lines · 73 tokens per session scan A 9dcf1629d386

Subscribe to this mod's changes

claim is a skill published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,977 once invoked, about $0.0004 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 2026-09-03.