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/cueapi/cueapi-cli/claude-mdgit clone --depth 1 https://github.com/cueapi/cueapi-cliWhat 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 | $0.00622 | $0.00622 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
cueapi-cli 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 yesterday.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Rules
Who Does What
Claude Code - writes code, opens PRs, merges when CI passes, deploys to staging and frontend sites Argus - tests staging, promotes to production, cuts PyPI release tags, tests docs and blog accuracy
PR Process - Non-Negotiable
Every change must go through a PR. No direct pushes to main under any circumstances. PRs are the permanent audit trail of every change made to this codebase. Claude Code opens PRs and merges them once CI passes. No human reviewer required. CI must pass before merging - no exceptions. Never bypass branch protection or force merge. Never merge a failing CI check - fix the root cause first.
Complete Pipeline
cueapi (hosted API - private repo)
Claude Code: code change -> open PR -> sdk-integration + deploy-staging CI must pass -> merge -> Railway staging deploy Argus: runs 246 staging tests -> all pass -> promotes to production
cueapi-core (open source)
Claude Code: code change -> open PR -> sdk-integration CI must pass -> merge Argus: runs full pytest suite -> confirms green
cueapi-python
Claude Code: code change -> open PR -> sdk-integration CI must pass -> merge Argus: runs SDK tests -> all pass -> cuts version tag -> PyPI auto-publishes
cueapi-cli
Claude Code: code change -> open PR -> test CI must pass -> merge Argus: runs CLI tests -> all pass -> cuts version tag -> PyPI auto-publishes
Marketing site (cueapi.ai)
Claude Code: code change -> open PR -> CI passes -> merge -> Cloudflare Pages auto-deploys to production Argus: not involved
Docs (docs.cueapi.ai)
Claude Code: code change -> open PR -> CI passes -> merge -> Cloudflare Pages auto-deploys Argus: crawls after deploy -> tests all code examples against real API -> verifies all links -> flags inaccuracies
Blog (blog.cueapi.ai)
Claude Code: code change -> open PR -> CI passes -> merge -> Cloudflare Pages auto-deploys Argus: crawls after deploy -> tests all code snippets -> verifies package versions -> flags inaccuracies
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.
- yesterday First seen · 65 lines · 622 tokens per session scan A d9a8877aec1b
cueapi-cli CLAUDE.md is an instructions file published in the GitHub repository cueapi/cueapi-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 622 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
deepagents AGENTS.md
Instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
autoharness AGENTS.md
Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
martex-quant CLAUDE.md
Instructions for martex-dev/martex-quant, covering session start — read these first, project instructions, ai trading bot project - master instructions, role and project objective.
ZipAgent AGENTS.md
Instructions for JiayuXu0/ZipAgent, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.