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 agentmods add instructions/djangopeng/agentic-ai/claude-mdgit clone --depth 1 https://github.com/DjangoPeng/agentic-aiWrote 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/djangopeng/agentic-ai/claude-md)<a href="https://agentmods.dev/instructions/djangopeng/agentic-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/djangopeng/agentic-ai/claude-md.svg" alt="Measured on agentmods" 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 | $0.03043 | $0.03043 |
| Opus 5 | $0.01522 | $0.01522 |
| Sonnet 5 | $0.00609 | $0.00609 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
agentic-ai CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Trigger a real audit run, then the governance / final-audit steps, via the dashboard or curl: How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository shape
This is a documentation-heavy course repository for OpenClaw + Claude Code production practice. It is not one buildable application: each runnable lesson project has its own directory, virtualenv, runtime artifacts, and README.
Main areas:
openclaw-infra/,openclaw-im/,openclaw-models/: deployment, IM integration, model/provider, security, and troubleshooting guides for OpenClaw.openclaw-soul/,openclaw-heartbeat/,openclaw-skills/: templates and examples for SOUL/AGENTS behavior files, Heartbeat/Cron automation, and SKILL.md authoring.xhs-auto-publisher/: Playwright-based Xiaohongshu publisher for authorized accounts, with human QR-login handoff and Lobster/Feishu notification payloads.financial-automation/: Python OCR/PDF extraction pipeline for invoices, validation, attachment upload, and Feishu Bitable write-back.morning-newspaper/: Python multi-source news collection pipeline with three LLM editorial gates, static dashboard generation, and Feishu delivery workflow.CRM-Assistant/: Python standard-library CLI that converts Feishu meeting raw data/transcripts into CRM assets and Feishu Bitable rows.ai-quant-cli/: Python CLI that parses A-share annual-report PDFs into structured financials; Claude Code itself performs the risk analysis (no LLM API in code), then scripts render charts and a single-page HTML investment report.github-secret-auditor/: OpenClaw Skill with no runnable code; it drives Claude Code over ACP to audit and remediate leaked secrets in an authorized GitHub repo, with OpenClaw handling review, commit/push, and the Feishu report.security-guardian/: runnable Python-stdlib web console (port 8511, no third-party deps) for pre-release security self-audit of a cloud OpenClaw; it read-only-collects and redacts OpenClaw evidence into a per-run manifest workspace, invokes Claude Code (claude -p) to analyze it and return JSON findings, then writes reports and a go/no-go decision — detection only, never auto-remediates production.
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 · 298 lines · 3,043 tokens per session scan A 8accaa7736e8
agentic-ai CLAUDE.md is an instructions file published in the GitHub repository DjangoPeng/agentic-ai (147 stars, last pushed 1mo ago), licensed MIT. It adds 3,043 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
TLDR AGENTS.md
Instructions for 0p9b/TLDR: @./skills/tldr/SKILL.md @./skills/tldr-commit/SKILL.md @./skills/tldr-review/SKILL.md @./skills/tldr-compress/SKILL.md.
elephant-agent copilot-instructions.md
Copilot instructions for agentic-in/elephant-agent, covering github copilot instructions, source of truth order, review priorities, harness-specific checks and validation expectations.
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.
harness-sdk CLAUDE.md
Claude Code instructions for strands-agents/harness-sdk, a project described as: Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
MassGen AGENTS.md
AGENTS.md instructions for massgen/MassGen, covering claude.md, openspec instructions, planning, instruction file parity and debugging assumptions.
PPTAgent CLAUDE.md
Claude Code instructions for icip-cas/PPTAgent, a project described as: An Agentic Framework for Reflective PowerPoint Generation.