Borrowing it
Nothing to install: this file belongs to pandazki/pneuma-skills. 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/pandazki/pneuma-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/pandazki/pneuma-skillsWrote 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/pandazki/pneuma-skills/agents-md)<a href="https://agentmods.dev/instructions/pandazki/pneuma-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pandazki/pneuma-skills/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/pandazki/pneuma-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pandazki/pneuma-skills/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 | $0.13732 | $0.13732 |
| Opus 5 | $0.06866 | $0.06866 |
| Sonnet 5 | $0.02746 | $0.02746 |
| Haiku 4.5 | $0.01373 | $0.01373 |
Grade A, and why
pneuma-skills AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Agent | Claude Code CLI stdio stream-json; Codex CLI `app-server` stdio JSON-RPC; Moonshot Kimi Code CLI ACP stdio JSON-RPC (`kimi acp`) — all via `node:child_process` | How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pneuma Skills
Single source of truth for agent instructions. Claude Code reads this via the one-line
@AGENTS.mdimport inCLAUDE.md; Codex and Kimi read this file directly. Never duplicate content intoCLAUDE.md— it must stay a single import line.Per-domain constraints and gotchas live in
.claude/rules/— before editing files in a domain, read the matching rule file (Claude Code auto-loads them by path; other agents must read them explicitly). Index in Development Toolchain.
Project Overview
Pneuma Skills is co-creation infrastructure for humans and code agents. Agents edit files directly (Read/Edit/Write); files remain the canonical collaboration surface. Viewers are live players for agent output, rendering work in domain terms (a deck, a board, a project) so humans can watch, intervene in the UI, or hand structured guidance back. Four pillars: a visual environment (live players with optional participation), skills (domain knowledge + seed templates + session persistence), continuous learning (evolution agent for cross-session preference extraction), and distribution (mode marketplace, publishing, sharing). Multiple agent backends (Claude Code, Codex, Kimi CLI) selected at startup.
Formula: ModeManifest(skill + viewer + agent_config) × AgentBackend × RuntimeShell
Version: 3.46.4
Runtime: Bun >= 1.3.14 (required, not Node.js)
Builtin Modes: webcraft, doc, slide, draw, diagram, illustrate, remotion, gridboard, kami, clipcraft, cosmos, wordtaste, bansho, eli5, plotwise, mode-maker, evolve, project-evolve, project-onboard, project-tidy
Modes can set
hidden: trueto disappear from user-pickable lists (launcher grids, ProjectPanel mode-tile picker). Their sessions are also stampedinternal: truebyscanProjectSessionsand filtered out of user-facing session lists (project panel, project cards, quick-resume). Internal modes (evolve,project-evolve,project-onboard,project-tidy) are hidden — triggered by specific UI affordances or programmatically, never by a "what mode to start?" choice.
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 Changed 52886f86d6f8
- 2d ago Changed fa451bf00fb3
- 3d ago Changed · +91 tokens per session e7e2856f7171
- 4d ago Changed baf38a820f8e
- 5d ago Changed 697a54526e06
- 6d ago Changed · +3 lines · +348 tokens per session 12724a608695
- 11d ago First seen · 479 lines · 13,293 tokens per session scan A b8040595711d
pneuma-skills AGENTS.md is an instructions file published in the GitHub repository pandazki/pneuma-skills (160 stars, last pushed yesterday), licensed MIT. It adds 13,732 tokens to every session, about $0.0687 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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.
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.