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 | $0.03483 | $0.03483 |
| Opus 5.5 | $0.01393 | $0.01393 |
| Sonnet 5.5 | $0.00697 | $0.00697 |
| Haiku 4.5 | $0.00348 | $0.00348 |
Grade A, and why
pneuma-skills 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.
How it starts
The opening of the file, as written. The whole thing — 247 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.This startup guide stays below 24 KiB so Codex can read it within its default instruction budget. Architecture details live in Project Guide. Before editing, read the matching domain rules below; their contents are shared by both harnesses.
Product and Architecture
Pneuma Skills is co-creation infrastructure for humans and code agents. It turns an agent's work into a domain-specific environment where a person can watch, participate, and carry the work forward. Four pillars support this: a visual environment, skills, continuous learning, and distribution.
- Shared work, two ways to interact. Agents use native file tools;
people see documents, decks, boards, and other domain objects. Files remain
the canonical surface for persistent work. Viewers consume typed Sources;
their optional edits return to the same files. Preserve the connection
between what the user points at, what the agent changes, and the visible
result.
ViewerAddressis the shared object-reference contract. - The viewer is a live player for the task. It renders work as it forms and supports direct edits, structured guidance, and inspection where useful. Design the experience around the person's task and the domain's units. Creation and consumption can have different interactions; partial, waiting, and failed states must remain understandable.
- A mode packages a way of working. Its domain model, skill, scripts, seeds,
viewer, and quality criteria belong together. The framework supplies shared
contracts and runtime services. Mode-specific knowledge stays in the mode;
backend-specific knowledge stays behind
BackendModule. Capabilities are explicit, so a backend need not pretend to support another backend's tools. - Spend agent judgment where it matters. Interpretation, creation, and tradeoffs need judgment. Established assembly, validation, scheduling, and deterministic interaction paths belong in programs. Put repeatable mechanics in scripts and explain their use in skills. Essential workflow policy must remain usable across the supported harnesses.
- Let collaboration accumulate. Sessions persist; optional projects connect work across modes through shared materials, context, and explicit handoffs. Preference skills maintain personal and project memory. Evolution proposes evidence-backed additions and removals to guidance for user review. Modes can be customized and distributed with their working methods intact.
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 c09358480178
- 12d ago Changed 198e28b7297b
- 14d ago Changed c5427eb5febd
- 15d ago Changed · +3 lines · +57 tokens per session 6a8fd857faa8
- 18d ago Changed f1522ab6e5c9
- 19d ago Changed 4c0de5d3a321
- 1mo ago Changed 3e063d3711dd
- 1mo ago Changed 9ebafa7313ed
- 1mo ago Changed 5e80cb1e847d
- 1mo ago First seen · 244 lines · 3,426 tokens per session scan A fc235de59dd3
pneuma-skills AGENTS.md is an instructions file published in the GitHub repository pandazki/pneuma-skills (161 stars, last pushed yesterday), licensed MIT. It adds 3,483 tokens to every session, about $0.0139 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.