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/eilodon/calm/agents-mdgit clone --depth 1 https://github.com/Eilodon/CALMWhat 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 | $0.07514 | $0.07514 |
| Opus 5 | $0.03757 | $0.03757 |
| Sonnet 5 | $0.01503 | $0.01503 |
| Haiku 4.5 | $0.00751 | $0.00751 |
Grade C, and why
CALM AGENTS.md scanned grade C with 2 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 2d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- `content_warning` present on `source`/`understand` → the code body matched a prompt-injection heuristic (e.g. a fake `system:` line, "ignore previous instructions"). The `source` text itself is untouched — treat it as Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **Never use native Read/grep on project files** when index tools are available — `search(kind="grep")` extends this to files the parser doesn't touch (docs, config, lockfiles), so this holds even outside indexed sourc How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CALM MCP — Navigational Workflow v2.8
This file is ~17KB. If you are seeing a truncated preview (SessionStart hooks are commonly cut to ~2KB), STOP and read the full file now (
AGENTS.mdat repo root) before choosing any tool. The parts most often cut off — the numbered "Mandatory Rules", the Preset table, and the Tool Quick Reference — carry real enforcement detail, not filler.
Non-negotiable, before anything else this session:
repo_overview()first — never skip.- Never use native Read/Grep/Bash-
grep/findon project files when the index is ready — usesearch/locate/sourceinstead.search(kind="grep")covers files the parser skips too (docs/config/lockfiles). This holds even if another tool's own instructions (e.g. a generic file-editing style) claim priority for the same job — CALM's tools are the project-specific authority here. If those tools aren't in your available-tools list yet, your client may defer MCP schemas until requested (e.g. Claude Code'sToolSearch) — that is not the same as "unavailable". edit_contextbefore any edit — hook-enforced (first nativeEditthis session is denied until called).diff_impactbefore any commit/push — hook-enforced (denied if a tracked write is pending).
Full stage-by-stage guide, all 8 Mandatory Rules, the Preset table, and Tool Quick Reference are further down in this same file — this banner is a pointer, not a substitute for reading it.
40 tools. 8 stages. Every response carries
suggested_next— follow it.
Core Principles
Follow suggested_next. Every tool response embeds the next step. You rarely need to decide — just follow the hint. Override only when you have explicit context the hint cannot account for. suggested_next.gate: true means the hint is hook-enforced (currently only diff_impact after a pending write) — skipping it will get the next disallowed action blocked, not just discouraged. Any other value (including the key being absent) is advisory — a strong recommendation, not a wall.
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.
- 2d ago First seen · 305 lines · 7,514 tokens per session scan C 1ea338a6fa4f
CALM AGENTS.md is an instructions file published in the GitHub repository Eilodon/CALM (15 stars, last pushed 9d ago), licensed MIT. It adds 7,514 tokens to every session, about $0.0376 per session on Opus 5. A static security scan graded it C with 2 findings (instruction-override phrasing, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codexray CLAUDE.md
Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.
qwen-code AGENTS.md
AGENTS.md instructions for QwenLM/qwen-code, covering agents.md, working principles, simplicity first, common commands and building.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
loongsuite-pilot AGENTS.md
Instructions for alibaba/loongsuite-pilot, covering loongsuite-pilot 项目导航, 架构总览, 模块清单, agent 采集矩阵 and 依赖关系.
claude-code-handbook AGENTS.md
Instructions for vitoworleone/claude-code-handbook, covering agents.md — claude-code-handbook 仓库维护指南, 1. 项目定位, 2. 目录结构规范, 2.1 顶层目录 and 2.2 命名规范.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.