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/chhuax/praxis-devos/claude-mdgit clone --depth 1 https://github.com/chhuax/praxis-devosWrote 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/chhuax/praxis-devos/claude-md)<a href="https://agentmods.dev/instructions/chhuax/praxis-devos/claude-md"><img src="https://agentmods.dev/badge/instructions/chhuax/praxis-devos/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 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
praxis-devos 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Claude Code 通过
CLAUDE.md读取项目指令；共享项目规则统一维护在AGENTS.md。 如需 Claude 专属补充，请只在此文件追加少量差异内容，不要复制AGENTS.md全文。
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Run all tests
node --test
# Run a single test file
node --test test/praxis-devos.test.js
# Run the CLI locally
node bin/praxis-devos.js --help
node bin/praxis-devos.js setup --project-dir /tmp/test-project
node bin/praxis-devos.js sync --project-dir /tmp/test-project
No build step — pure ESM, runs directly with Node >=20.19.0.
Release safety rules
- Never publish a new npm version, push release tags, or perform other release actions before explicitly confirming the release order with the user.
- For release work, confirm whether the intended order is PR first, merge first, publish first, and tag before taking any release action.
- Do not assume publish-before-merge is acceptable.
Architecture
praxis-devos is a CLI tool that installs OpenSpec governance + SuperPowers execution rules into a user's project, then projects skills into agent-specific directories so each coding agent (Claude Code, OpenCode, Codex) discovers them natively.
Core flow (src/core/praxis-devos.js)
All CLI commands are handled here: setup, sync, teardown, migrate. This file parses args, resolves skill sources from src/, and orchestrates projection.
Projection layer (src/projection/)
Each agent has its own projector:
claude.js→ writes~/.claude/skills/<name>/SKILL.md(skill dirs)opencode.js→ writes~/.claude/skills/<name>/SKILL.md(skill dirs)codex.js→ writes~/.codex/skills/<name>/SKILL.md(skill dirs)index.js— dispatches to the right projector based on selected agentsmarkers.js— injects/parses<!-- PRAXIS_PROJECTION ... -->markers so projections can be identified and cleaned up later
Key design decisions
- Skills are stamped with a version marker on write. On
sync, stale projections (marker present but name no longer in the skill set) are removed. src/templates/managed-entry.mdis the template injected into a user project'sAGENTS.md/CLAUDE.mdduringsetup. It contains the OpenSpec flow gating rules.- OpenCode integration relies on projected skills/commands plus runtime config cleanup; do not reintroduce a Praxis OpenCode plugin entrypoint.
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.
- 5d ago First seen · 56 lines · 642 tokens per session scan A 34d6813e492b
praxis-devos CLAUDE.md is an instructions file published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 642 tokens to every session, about $0.0032 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.