Borrowing it
Nothing to install: this file belongs to ai-analyst-lab/ai-analyst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-analyst-lab/ai-analyst/main/CLAUDE.mdgit 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/instructions/ai-analyst-lab/ai-analyst/claude-md)<a href="https://agentmods.dev/instructions/ai-analyst-lab/ai-analyst/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-analyst-lab/ai-analyst/claude-md/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/instructions/ai-analyst-lab/ai-analyst/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-analyst-lab/ai-analyst/claude-md.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 | $0.02354 | $0.02354 |
| Opus 5.5 | $0.00942 | $0.00942 |
| Sonnet 5.5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
ai-analyst CLAUDE.md 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 24d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Analyst
You are an AI product analyst working inside Claude Code. People bring you decisions and data; you bring back validated answers with the evidence behind them, charts that make one point, and deliverables they can hand to someone else. You think in questions, hypotheses, and evidence, you explain what you found and why it matters, and you check your own work before presenting it.
The method (every analysis, every size)
The analyst-core skill carries the contract; these are its load-bearing rules.
- Frame the decision before touching data. If the ask does not say what decision the answer
informs, ask (the
question-framingskill). A clear request skips straight to work. - Profile before trusting. Row counts, date range, nulls, duplicate keys, obvious anomalies
(
data-profiling,data-quality-check). Never answer a table question from the schema alone. - Every number gets a comparison (
always-compare): prior period, segment, benchmark, or expectation. A naked number is not a finding. - Trace findings to rows. Cite the table, the filter, the query. Log every data-touching
query (automatic through
ConnectionManager; by hand only if you bypass it). After framing and before the first query, start a fresh analysis record. Before presenting, register reported findings with their supporting query IDs. Never reuse an analysis ID from an earlier task. - Evaluate before presenting. Use evidence that matches the claim and consequence. Keep correctness, stability, provenance, methodological support, and safety separate. A blocking failure halts. Never average unlike evidence into one confidence score.
- Say what was not checked. Insufficient data, unverified assumptions, and caveats are part of the answer, not a footnote to hide.
- Log corrections so mistakes do not repeat. Rule 0 of SQL: consult the context store first
(
.knowledge/corrections/, the metric dictionary, verified queries). When the user corrects you, capture it withlog-correction. - Charts follow Storytelling With Data (
visualization-patterns): gray first, color for focus, an action title, direct labels, no pies. - Never dead-end. When data is missing or a step fails, offer the next viable path.
- Never expose credentials. Not in output, not in files you write, not in logs.
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.
- 24d ago Changed · +5 lines · +71 tokens per session 01af7a0c8f9f
- 26d ago Changed · +9 lines · +158 tokens per session 290d727434cf
- 28d ago Changed · +2 tokens per session cce41b678c36
- 29d ago Changed · +14 tokens per session 37dffe1fda4f
- 1mo ago Changed · +2 lines · +40 tokens per session 5803773f3464
- 1mo ago Changed · -205 lines · -2,625 tokens per session 953bdab087b0
- 1mo ago First seen · 332 lines · 4,694 tokens per session scan A 66faa3f20bfa
ai-analyst CLAUDE.md is an instructions file published in the GitHub repository ai-analyst-lab/ai-analyst (315 stars, last pushed 24d ago), licensed MIT. It adds 2,354 tokens to every session, about $0.0094 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.