Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/lambda-symbolics/autolith/agents-mdgit clone --depth 1 https://github.com/lambda-symbolics/autolithWhat 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 | $0.02817 | $0.02817 |
| Opus 5 | $0.01409 | $0.01409 |
| Sonnet 5 | $0.00563 | $0.00563 |
| Haiku 4.5 | $0.00282 | $0.00282 |
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 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 — 299 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 and macOS arm64 on SBCL with a terminal interface, one primary agent, and no claim of hostile-code sandboxing. Nix builds support Linux x86-64 and macOS arm64. Packaged binary releases support Linux x86-64 and aarch64 with glibc or musl, macOS x86-64 and arm64, FreeBSD x86-64, NetBSD x86-64, and OpenBSD x86-64.
Upstream References
When a change depends on established behavior in another agent, inspect a current upstream checkout outside this Git worktree. Keep reference checkouts read-only, record the repository URL and exact inspected commit in the review notes, and refresh the checkout before making claims about current behavior. References are research inputs, not Autolith dependencies; do not edit them or copy their architecture wholesale.
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 First seen · 299 lines · 2,817 tokens per session scan A 1355d5a2fcec
autolith AGENTS.md is an instructions file published in the GitHub repository lambda-symbolics/autolith (261 stars, last pushed 2d ago), licensed ISC. It adds 2,817 tokens to every session, about $0.0141 per session on Opus 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
Lody AGENTS.md
Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
supercli AGENTS.md
Instructions for yashdev9274/supercli, covering agent instructions for supercode monorepo, build commands, root level commands, individual app/package commands and package-specific commands (run from package directory).
senpi AGENTS.md
Instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.
cocode AGENTS.md
Instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
copperhead AGENTS.md
Instructions for copperheadhq/copperhead, covering agents.md, repository overview, sources of truth, build and verification and architecture.