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.
git 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/commands/ai-analyst-lab/ai-analyst/analyst)<a href="https://agentmods.dev/commands/ai-analyst-lab/ai-analyst/analyst"><img src="https://agentmods.dev/badge/commands/ai-analyst-lab/ai-analyst/analyst/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/commands/ai-analyst-lab/ai-analyst/analyst"><img src="https://agentmods.dev/badge/commands/ai-analyst-lab/ai-analyst/analyst.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 | $0.00019 | $0.00458 |
| Opus 5.5 | $0.00008 | $0.00183 |
| Sonnet 5.5 | $0.00004 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
analyst 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 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.
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.
What it actually says
Start a data analysis using the AI Analyst method. The user's request: $ARGUMENTS
Follow the analyst-core skill's rules for the whole session. Concretely:
-
Frame first. If $ARGUMENTS is empty or does not state the decision the analysis will inform, ask for it before touching data. Use the question-framing skill to establish goal, decision, metric, and hypotheses. If the request is already clearly framed, confirm the framing in one or two sentences and proceed.
-
Select context. Run the knowledge-bootstrap skill to resolve the active context source and load only the small resident layer. Once the exact question is known, run the context-trace skill. Open the files named in the manifest's selected items and use only that question-specific bundle. Do not load every metric, example, correction, and prior analysis by default. Stop on a blocking conflict. Name stale or missing review evidence before relying on it.
-
Profile the data. Run the data-profiling and data-quality-check skills on the files or tables involved: row counts, date ranges, nulls, duplicate keys, anomalies. Report what you found before analyzing.
-
Analyze. Do the comparison the question needs (segment, funnel, trend, decomposition). Every number carries a comparison per the always-compare skill. Build any chart with the visualization-patterns skill.
-
Validate. Trace every headline number to its source rows. Sum parts back to totals. Cross-check with the triangulation and trace skills. Reconcile the supplied context item IDs against citations and SQL-use evidence. A context manifest proves supply, not use or correctness.
-
Deliver. Save real files to the working folder: a written brief with a Checks section (what was verified, what was not), plus charts as PNGs. Log any correction the user makes to
.knowledge/corrections/.
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 · 39 lines · 19 tokens per session scan A da9f6f1b6a20
analyst is a command published in the GitHub repository ai-analyst-lab/ai-analyst (307 stars, last pushed 15d ago), licensed MIT. It adds 19 tokens to every session and 458 once invoked, about $0.0001 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 2026-09-12.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.