Puppyone is a Git-based context store for AI agents, giving each agent or tool controlled access to specific files through separate access points. Teams use it to share versioned context with agents through the command line, MCP, Git, shell access, or a web app. Its catalogue entries provide commands and instructions for working with Puppyone.
Borrowing it
Nothing to install: this file belongs to puppyone-ai/puppyone. 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/puppyone-ai/puppyone/main/AGENTS.mdgit clone --depth 1 https://github.com/puppyone-ai/puppyoneWrote 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/puppyone-ai/puppyone/agents-md)<a href="https://agentmods.dev/instructions/puppyone-ai/puppyone/agents-md"><img src="https://agentmods.dev/badge/instructions/puppyone-ai/puppyone/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/puppyone-ai/puppyone/agents-md"><img src="https://agentmods.dev/badge/instructions/puppyone-ai/puppyone/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 | $0.01141 | $0.01141 |
| Opus 5.5 | $0.00456 | $0.00456 |
| Sonnet 5.5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
puppyone 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Working Agreement
This file defines the default Git and delivery workflow for the entire PuppyOne Desktop repository. More specific AGENTS.md files may add rules for their own subdirectories.
Documentation Authority
- Current Desktop product, architecture, operations, privacy, release, and source-control documentation lives in
puppy-issues/document/puppyone-desktop. - This repository has no
docs/directory. Do not add current specifications or runbooks to it. archive/legacy-desktop-docs/is a frozen, non-canonical historical snapshot. Never use it to decide current behavior or implementation direction, and do not make code, tests, benchmarks, or quality gates depend on it.puppy-issues/document/product-philosophy.mdis the authority for the concepts users face and for user-facing wording. Its Vocabulary table decides which words may appear inlocales/renderer/**;npm run check:boundariesenforces it throughscripts/check-user-vocabulary.mjs, whose rules are generated from that table. Widen or narrow an exception by editing the table and runningnode scripts/check-user-vocabulary.mjs --sync, never by editing the generated rules or the violation baseline.- When implementation changes affect documented behavior, update the canonical
puppy-issuesdocument in the same delivery window and include a source link usingrepository@commit:pathprovenance.
Canonical Branches
mainis the protected stable and release branch. It must always represent a published or release-ready state.qubitsis the single integration branch for the next desktop release.- Do not develop directly on
main. Changes reachmainonly through the release and promotion workflow. - After every release, synchronize
qubitsto the releasedmaincommit before starting new feature work. Prefer a fast-forward; rebase only local, unpublished commits when necessary. - Release branches are temporary. Delete them after the release is verified and
qubitshas been synchronized.
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.
- 3d ago Changed · -4 tokens per session 62928a147b17
- 10d ago Changed · +1 lines · +130 tokens per session 6a0974ae336a
- 1mo ago Changed · -355 lines · -4,296 tokens per session 4a36cfe69e4c
- 2mo ago First seen · 415 lines · 5,311 tokens per session scan A f5d6b04122d6
puppyone AGENTS.md is an instructions file published in the GitHub repository puppyone-ai/puppyone (1,429 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,141 tokens to every session, about $0.0046 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.
puppyone AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| puppyone AGENTS.mdpuppyone-ai/puppyone | Instructions file | 1.4k | yesterday | Apache-2.0 | A | 1,141 | 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 | today | 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 |