dev AGENTS.md

Organization-wide instructions for coding agents working on repositories owned by the plasma-ai development organization.

In plain words
What is it for?
Use them as guidance when an agent works in one of the organization's repositories and needs to follow its communication and workflow conventions.
Why use it?
They give agents consistent rules for answering questions, planning work, editing files, and using Git across the organization's projects.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/plasma-ai/dev/agents-md
Clone the repo
git clone --depth 1 https://github.com/plasma-ai/dev

Made for: Codex, OpenCode.

Per session 5,117 This file is loaded in full into every session.
When invoked 5,117 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05117 $0.05117
Opus 5 $0.02559 $0.02559
Sonnet 5 $0.01023 $0.01023
Haiku 4.5 $0.00512 $0.00512

Measured yesterday against content hash 4592a5e84141, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev 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 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.

AGENTS.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

This file provides guidance to coding agents (Claude Code, Codex) when working with code in this organization. It is the org-wide root file — every repository under the org loads it alongside its own AGENTS.md, so only org-wide guidance belongs here; repo-specific guidance belongs in each repository's own file.

Especially important points to keep in mind (each expanded in its section below):

  • Questions are not edit requests. When a message asks a question without explicitly requesting a change, answer and stop (Communication).
  • Write clear and concise English. Write clear, concise, plain English which can be quickly and easily parsed by the user - answer questions directly in short form unless elaboration is requested (Writing Style).
  • Seek the best solution, not agreement. When you think the user is wrong, don't be afraid to say so — the right answer matters more than the path of least resistance (Pushing Back).

Workflow

Git Workflow

  • Do not create git commits unless explicitly asked. Never auto-commit during implementations.
  • Never touch the staging area or stash. Do not run git add, git reset, git stash, git checkout -- <file>, git restore, git clean, or any other command that stages, unstages, stashes, or discards changes. The user uses the staging area to track approved work — modifying it destroys their workflow. This applies even when debugging (e.g. do not stash to test original code — use git show HEAD:<file> or git diff HEAD to inspect the original state without modifying the working tree).
  • Leave all committing to the user. Make code changes, run tests, run pre-commit, but stop before committing.
  • No session identifiers or tool footers in anything published. Commit messages end at the co-author trailer (Co-Authored-By: ...) — never append session or conversation identifiers, links back into an agent harness, or trailers of that kind (e.g. Claude-Session:) to commits, PR or issue bodies, comments, release notes, or any committed file. Do not add "Generated with ..." footers or tool badges to PRs or issues either; the co-author trailer is the only attribution that belongs anywhere. Harness trailers found in existing git history are a defect being scrubbed, not a pattern to imitate.
  • Exception for fractal. When running the /fractal skill or operating a fractal node, commit fractal's own setup/seed/config artifacts autonomously and without asking — fractal init's output (.fractal/ and the wiki scaffold it creates), the node seed, and the baseline and child config commits the fractal skill instructs you to make. Never ask the user whether to commit them. Ordinary project work in the user's main worktree still follows the rules above.

Read the full file on GitHub · 410 lines

Changes

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.

  1. yesterday First seen · 410 lines · 5,117 tokens per session scan A 4592a5e84141

Subscribe to this mod's changes

dev AGENTS.md is an instructions file published in the GitHub repository plasma-ai/dev (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,117 tokens to every session, about $0.0256 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens