A search tool for an experiment run index and its research notes. It finds runs by tag, date, type, claim, or free-text terms and returns pointers instead of loading raw data.

Use it to find recent runs, runs connected to a claim, experiments of a certain type, or runs matching a tag or date.

It helps you locate relevant experiment history without manually browsing many files or reading every result.

How swarm-ai-research/swarm configures Claude Code

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/run-query/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/swarm-ai-research/swarm/run-query/github.svg)](https://agentmods.dev/skills/swarm-ai-research/swarm/run-query)

Your own site

<a href="https://agentmods.dev/skills/swarm-ai-research/swarm/run-query"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/run-query/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/swarm-ai-research/swarm/run-query"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/run-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 470 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00470
Opus 5	$0.00017	$0.00235
Sonnet 5	$0.00007	$0.00094
Haiku 4.5	$0.00003	$0.00047

Measured 6d ago against content hash 519f776f0e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-query 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.

.skills/run-query/SKILL.md · 61 lines

What it actually says

EXECUTE NOW

Query: $ARGUMENTS

Parse the query type:

tag <tag> — find runs by tag
date <YYYY-MM-DD> or date <YYYY-MM> — find runs by date
type <single|sweep|redteam|study|calibration> — find runs by type
claim <claim-id> — find runs linked to a claim
recent [N] — show N most recent runs (default 10)
stats — show run index statistics
Free text — search run-index.yaml and vault for matches

Execution

Source files

Run index: /Users/raelisavitt/swarm-artifacts/run-index.yaml
Vault claims: /Users/raelisavitt/swarm-artifacts/vault/claims/
Vault experiments: /Users/raelisavitt/swarm-artifacts/vault/experiments/
Run metadata: /Users/raelisavitt/swarm-artifacts/runs/<run_id>/run.yaml

For tag queries

Search run-index.yaml for entries where tags contains the search term.

For claim queries

Read the claim file at vault/claims/<claim-id>.md
Extract run references from evidence.supporting and evidence.weakening
Look up each run in run-index.yaml
Return a summary table

Output format

## Run Query Results: {query}

| Date | Run ID | Type | Tags | Key Finding |
|------|--------|------|------|-------------|
| ... | ... | ... | ... | ... |

{N} runs matched.

For individual run details, also show:

Hypothesis
Parameters swept
Primary result
Claims affected
Reproduction command

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.

6d ago First seen · 61 lines · 34 tokens per session scan A 519f776f0e16

Subscribe to this mod's changes

run-query is a skill published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 470 once invoked, about $0.0002 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.

Research agi-safety ai ai-agent ai-agents clawxiv openclaw

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

HKUDS/nanobot · 22 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

swarm: Skill for Claude Code