Borrowing it
Nothing to install: this file belongs to lambda-symbolics/autolith. 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/lambda-symbolics/autolith/master/AGENTS.mdgit clone --depth 1 https://github.com/lambda-symbolics/autolithWrote 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/lambda-symbolics/autolith/agents-md)<a href="https://agentmods.dev/instructions/lambda-symbolics/autolith/agents-md"><img src="https://agentmods.dev/badge/instructions/lambda-symbolics/autolith/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/lambda-symbolics/autolith/agents-md"><img src="https://agentmods.dev/badge/instructions/lambda-symbolics/autolith/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 | $0.04920 | $0.04920 |
| Opus 5.5 | $0.01968 | $0.01968 |
| Sonnet 5.5 | $0.00984 | $0.00984 |
| Haiku 4.5 | $0.00492 | $0.00492 |
Grade A, and why
autolith 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Purpose and Sources of Truth
Autolith is a small, live, self-modifying Common Lisp agent. This file contains
its enduring architectural and repository policy. docs/guide.org documents
user-visible behavior, docs/architecture.org maps runtime and source
boundaries, and tracked source plus behavioral tests are executable truth. Do
not create another omnibus product specification.
Core principles:
- Treat the live Lisp image as the primary runtime while keeping source sufficient for a clean rebuild.
- Prefer Common Lisp and focused CLOS protocols over generated scripts, parallel type dispatch, duplicated data structures, or overlapping public interfaces.
- Keep self-modification explicit, auditable, reconstructible, and confined to a small operation set.
- Preserve durable conversations, user state, working generations, and a pristine recovery path.
- Use process boundaries for reliability and accidental-damage containment, never as a hostile-code security claim.
- Keep platform-specific behavior behind narrow adapters.
- Treat migrations and compatibility readers as temporary release machinery. Give them an explicit removal boundary instead of accumulating them forever.
Do not leave TODOs, FIXMEs, stubs, placeholders, or knowingly partial implementations. If a requirement is genuinely too broad or conflicts with another requirement, stop and ask.
Supported source-development targets are Linux x86-64, macOS arm64, and Windows x86-64 on SBCL with a terminal interface, one primary agent, and no claim of hostile-code sandboxing. Nix builds support Linux x86-64 and macOS musl, macOS x86-64 and arm64, FreeBSD x86-64, NetBSD x86-64, OpenBSD x86-64, and Windows x86-64.
Host differences live behind the platform protocol in src/core/platform.lisp
with one adapter per host family; #+win32 appears only in those adapters, in
autolith.asd feature expressions, and in the standalone scripts that run
before the system loads. Windows supports supervised detached sessions and
exact-heap restart checkpoints, while withholding fork-based image saves and
filesystem sockets. Windows commands use the native AppContainer
helper with explicit workspace, private temporary, and read-only tool scopes. Checks
that depend on POSIX facilities go through the test fixture protocol in
tests/test-support.lisp and are recorded as skipped where the host lacks
them. Sources and tests alike change the environment through
platform-setenv and platform-unsetenv, resolve links through
platform-truename, and remove trees through platform-delete-directory-tree,
never through sb-posix, truename, or uiop:delete-directory-tree
directly: Windows keeps two environments, leaves links unresolved in
truename, and refuses to delete read-only files. Names carrying pathname
metacharacters or backslashes belong only behind the :wildcard-file-names
fixture.
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 · +6 lines · +48 tokens per session 41026de7e8ea
- 7d ago Changed · +7 lines · +53 tokens per session 9e267135d08d
- 9d ago Changed · +5 lines · +51 tokens per session 430250f11159
- 10d ago Changed · +7 lines · +138 tokens per session d0d8584df507
- 11d ago Changed · +39 lines · +444 tokens per session d265e5aa3973
- 18d ago Changed · +5 lines · +54 tokens per session d38707a676ec
- 20d ago Changed · +3 lines · +43 tokens per session 3226d3c6de39
- 21d ago Changed · +7 lines · +54 tokens per session 5dc25b96103e
- 1mo ago Changed · +1 lines · +30 tokens per session eaaf1a2ec81a
- 1mo ago First seen · 389 lines · 4,005 tokens per session scan A 58992c2d7176
autolith AGENTS.md is an instructions file published in the GitHub repository lambda-symbolics/autolith (533 stars, last pushed yesterday), licensed ISC. It adds 4,920 tokens to every session, about $0.0197 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.
autolith AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| autolith AGENTS.mdlambda-symbolics/autolith | Instructions file | 533 | yesterday | ISC | A | 4,920 | 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 |