Borrowing it
Nothing to install: this file belongs to baalimago/slivingdoc. 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/baalimago/slivingdoc/master/AGENTS.mdgit clone --depth 1 https://github.com/baalimago/slivingdocWrote 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/baalimago/slivingdoc/agents-md)<a href="https://agentmods.dev/instructions/baalimago/slivingdoc/agents-md"><img src="https://agentmods.dev/badge/instructions/baalimago/slivingdoc/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/baalimago/slivingdoc/agents-md"><img src="https://agentmods.dev/badge/instructions/baalimago/slivingdoc/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 | $0.08373 | $0.08373 |
| Opus 5.5 | $0.03349 | $0.03349 |
| Sonnet 5.5 | $0.01675 | $0.01675 |
| Haiku 4.5 | $0.00837 | $0.00837 |
Grade A, and why
slivingdoc 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 9d 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 — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — slivingdoc
Architecture docs
architecture/ holds one doc per command and subsystem: an overview, the
product contract, pull, commit, conflicts, checkpoints, the notebook, the Git
engine, the workspace, storage, the S3 store, hosted storage mode, login and
storage selection, the CLI, the terminal presentation,
the MCP server, configuration, errors, logging, security, guarantees,
testing, build, releasing, running, and recorded decisions. Start at
architecture/README.md: it indexes every doc
with a one-line summary and suggests a reading order per task. Open the
doc for your concern before scanning the code; it lists the files and
symbols to read.
Keep them true. The docs are only useful if an agent can trust them without re-checking the code:
- A change that alters behavior, a flow, a file's role, a public name, a flag, an error code, an invariant, or a rule described in an architecture doc updates that doc in the same commit.
- A new command or subsystem gets a new
architecture/<concern>.mdin the same shape (intro with "Read this when", Key files, Flow, Behavior, Gotchas, Related) and a line inarchitecture/README.md. A removed or renamed file or symbol is removed or renamed in every doc that cites it. - Code comments cite a doc by path (
architecture/commit.md), never by section number or line. - Cite files and symbols, never line numbers. Describe only what the code does; plans go in worklogs or issues.
- If you find a doc that disagrees with the code, the code wins: fix the doc in your change, or say so if you cannot.
Architecture
slivingdoc is a standalone MCP server that gives many agents one shared
directory of UTF-8 text notes, stored durably in S3-compatible object storage
or, when SLIVINGDOC_TOKEN is set or slivingdoc login stored an account
login, in a space of the slivingdoc hosted storage API
(architecture/hosted-mode.md, architecture/login.md). It uses Git data structures and merge behavior internally but never invokes a
Git executable and never exposes a Git repository. The contract is split
by concern under architecture/. Three states
shape every operation. L is the caller-controlled visible directory.
P is the server-owned private state (repository, baseline, locks).
R is the accepted remote state indexed by the stored object current.
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.
- 9d ago Changed · +4 lines · +66 tokens per session d52cbc2b8386
- 14d ago Changed · +46 lines · +706 tokens per session b11797d11be0
- 1mo ago Changed · +1 lines · +37 tokens per session d876d7f60d5a
- 1mo ago Changed · +11 lines · +130 tokens per session c6611ce21c4b
- 1mo ago Changed · +6 lines · +148 tokens per session 4ee3963044fc
- 1mo ago Changed · +43 lines · +625 tokens per session 17ccac1dbc17
- 1mo ago Changed · +49 lines · +675 tokens per session 8966b2475aa9
- 1mo ago Changed · +10 lines · +175 tokens per session 22ac9cc7fbad
- 1mo ago Changed · -45 lines · -230 tokens per session 4f21f7b1af62
- 1mo ago First seen · 505 lines · 6,041 tokens per session scan A 53294658ac32
slivingdoc AGENTS.md is an instructions file published in the GitHub repository baalimago/slivingdoc (7 stars, last pushed 10d ago), licensed MIT. It adds 8,373 tokens to every session, about $0.0335 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 2026-08-31.
slivingdoc AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| slivingdoc AGENTS.mdbaalimago/slivingdoc | Instructions file | 7 | 10d ago | MIT | A | 8,373 | 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 |