Borrowing it
Nothing to install: this file belongs to chhuax/praxis-devos. 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/chhuax/praxis-devos/main/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/chhuax/praxis-devos/agents-md"><img src="https://agentmods.dev/badge/instructions/chhuax/praxis-devos/agents-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/chhuax/praxis-devos/agents-md"><img src="https://agentmods.dev/badge/instructions/chhuax/praxis-devos/agents-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 | $0.01367 | $0.01367 |
| Opus 5.5 | $0.00547 | $0.00547 |
| Sonnet 5.5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
praxis-devos AGENTS.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 2mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This block is maintained by Praxis DevOS. Run
npx praxis-devos updateto refresh it.
Flow Selection
- Enter an OpenSpec proposal flow for medium or large changes, cross-module changes, interface or compatibility changes, architecture or process refactors, or any request with unclear requirements, unresolved
open questions, or competing solution options. - In those cases, start with the OpenSpec proposal or exploration stage and finish clarification and option comparison inside the current OpenSpec stage before implementation.
- Use the OpenSpec implementation stage only for small, local implementation work with low ambiguity and no proposal need.
- Reviews and audit-style requests should follow the review flow.
- Routing examples — requests that REQUIRE proposal first: "帮我加一个 X"、"新增 Y 能力"、"我想做一套 Z workflow"、"add a release kit"、"implement feature X". These introduce new capabilities or cross-cutting concerns and must go through proposal first.
- Routing examples — requests that can use the implementation stage directly: "修一下这个 bug"、"改一下这段文案"、"update the version number"、"fix the failing test". These are small, scoped fixes with no design ambiguity.
Project Reading Order
- On first entry, read
docs/surfaces.yamlfirst. - Read
docs/codemaps/project-overview.mdif needed. - Read other
docs/codemaps/**artifacts on demand rather than by default.
OpenSpec + Superpowers Contract
- Inside OpenSpec, exploration, proposal, implementation, and archive are the only visible workflow layer.
- Superpowers may run only as embedded capabilities inside the active OpenSpec stage.
- Do not re-announce
Using [skill]orsuperpowers:<skill>, and do not create a second workflow, second wrap-up, or separate document tree. - Keep all stage-local outputs under
openspec/changes/<change>/...; do not writedocs/superpowers/.... - Capability execution is judged by evidence in the user-level Praxis state directory, not by user-visible announcements.
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.
- 2mo ago First seen · 94 lines · 1,367 tokens per session scan A eaccf8389863
praxis-devos AGENTS.md is an instructions file published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,367 tokens to every session, about $0.0055 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.
praxis-devos AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| praxis-devos AGENTS.mdchhuax/praxis-devos | Instructions file | 21 | 6mo ago | Apache-2.0 | A | 1,367 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |