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 ai-analyst-lab/ai-analyst --skill runsgit clone --depth 1 https://github.com/ai-analyst-lab/ai-analystWrote 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/ai-analyst-lab/ai-analyst/runs)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/runs"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/runs/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/ai-analyst-lab/ai-analyst/runs"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/runs.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 | $0.00229 | $0.02460 |
| Opus 5.5 | $0.00092 | $0.00984 |
| Sonnet 5.5 | $0.00046 | $0.00492 |
| Haiku 4.5 | $0.00023 | $0.00246 |
Grade C, and why
runs scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. On confirmation, remove the directories using `rm -rf` How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Runs
Purpose
Browse, inspect, compare, and clean up past pipeline runs. Each run is a
self-contained directory under working/runs/ with its own working files,
outputs, and pipeline state.
Architecture: Understanding the Two-Source System
The AI Analyst tracks analysis work in two independent locations:
-
Active Pipeline Runs (
working/runs/)- Contains in-progress, recently completed, or failed pipeline executions
- Each run is a directory with
pipeline_state.jsontracking agent progress - Used for resuming interrupted work and debugging issues
- Cleaned up periodically (30-day retention by default)
-
Archived Analyses (
.knowledge/analyses/)- Contains completed analyses that have been formally archived
- Includes validation grades, key findings, and links to outputs
- Permanent knowledge base for organizational learning
- Survives even after working/runs/ cleanup
Why this matters: A user asking "what analyses have I run?" expects to see BOTH in-progress work (working/runs/) AND completed archived work (.knowledge/analyses/). Missing either source gives an incomplete picture.
When to Use
- User says
/runs,/runs list,/runs latest,/runs clean, or/runs compare - When the user wants to see what analyses have been executed
Invocation
/runsor/runs list-- list all past runs/runs latest-- show details of the most recent run/runs {id}-- show details of a specific run (partial match supported)/runs clean-- remove runs older than 30 days (confirmation required)/runs compare {id1} {id2}-- compare two runs side by side
Instructions
Step 1: Determine Command Type
Parse the user's command to understand which operation they want:
- List:
/runsor/runs list→ requires dual-source scanning - Latest:
/runs latest→ single source (working/latest symlink) - Detail:
/runs {id}→ single source (working/runs/) - Compare:
/runs compare {id1} {id2}→ single source (working/runs/) - Clean:
/runs clean→ single source (working/runs/)
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.
- 1mo ago First seen · 219 lines · 229 tokens per session scan C 344a02d92999
runs is a skill published in the GitHub repository ai-analyst-lab/ai-analyst (322 stars, last pushed 1mo ago), licensed MIT. It adds 229 tokens to every session and 2,460 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
runs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| runsai-analyst-lab/ai-analyst | Skill | 322 | 1mo ago | MIT | C | 229 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |