What is fsl CLAUDE.md?

Project instructions for developing fsl, including its authoritative Rust code, design documents, current task state, implementation rules, and verification expectations. They also mark part of the project as a compatibility and language-server surface unless a task explicitly includes it.

Use them when starting or resuming work on fsl, especially before substantial implementation. They guide repository inspection, task setup, source selection, change scope, and testing.

They help an agent distinguish implemented behavior from proposals or old notes and make the smallest safe change. This reduces the risk of editing the wrong source or violating project decisions.

fsl CLAUDE.md — Instructions file for coding agents by ymm-oss: Project instructions for developing fsl, including its authoritative Rust…

Install

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.

agentmods

npx agentmods add instructions/ymm-oss/fsl/claude-md

Clone the repo

git clone --depth 1 https://github.com/ymm-oss/fsl

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ymm-oss/fsl/claude-md.svg)](https://agentmods.dev/instructions/ymm-oss/fsl/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ymm-oss/fsl/claude-md"><img src="https://agentmods.dev/badge/instructions/ymm-oss/fsl/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 615 This file is loaded in full into every session.

When invoked 615 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00615	$0.00615
Opus 5	$0.00308	$0.00308
Sonnet 5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 4d ago against content hash cf08548b14ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fsl CLAUDE.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 4d 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

Claude Code instructions

Sources of truth

The working tree and verified repository artifacts are current state; conversation history is not.
The native Rust workspace is authoritative. Treat src/fslc/ as a frozen compatibility/LSP surface unless the requested outcome explicitly crosses that boundary.
Accepted decisions live in docs/DESIGN-*.md. Current task state lives in .claude/work/active.md when that local file exists.
Do not treat proposals, plans, auto memory, or an earlier session's claims as implemented behavior.

Starting or resuming work

Inspect git status --short and the relevant implementation before editing.
If .claude/work/active.md exists, compare it with the working tree and report stale claims.
For a substantial task, use /task-start to create or refresh the task packet before implementation.
State the requested outcome, affected authority surface, invariant, and narrow verification plan.
Do not read unrelated directories without a concrete reason.

Implementation policy

Prefer the smallest contract-preserving change. Do not add fallback behavior or compatibility work unless the requirement or an established public contract calls for it.
For new language behavior, change the Rust implementation first. Change the frozen Python reference only when an accepted compatibility decision requires both implementations to move.
Preserve the runtime/solver dependency boundary and symbolic/concrete/BFS agreement.
Keep CLI stdout machine-readable where the command contract requires JSON; diagnostics and progress belong on the established channel.
Never suppress an error, weaken a spec, hand-edit a generated snapshot, or expand an allowlist merely to make a check green.

Verification and review

Run the narrowest relevant Rust test or native fslc command first.
Inspect the diff and exercise the changed contract with positive, negative, and boundary evidence.
Run broader Rust, compatibility, or browser gates in proportion to the affected surface.
Use the specialized FSL reviewers after semantics, coupled language files, or specs change.
To review a pull request that resolves an issue, use /pr-review; it orchestrates the specialized reviewers and never merges.
Before ending or compacting substantial work, run /checkpoint and preserve exact test outcomes.

Read the full file on GitHub · 53 lines

Changes

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.

4d ago First seen · 53 lines · 615 tokens per session scan A cf08548b14ec

Subscribe to this mod's changes

fsl CLAUDE.md is an instructions file published in the GitHub repository ymm-oss/fsl (23 stars, last pushed today), licensed Apache-2.0. It adds 615 tokens to every session, about $0.0031 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.

Code review LLM Python bounded-model-checking formal-methods formal-specification model-checking

mem0 AGENTS.md

AGENTS.md instructions for mem0ai/mem0, covering agents.md, do not, where to look, repository map and setup.

mem0ai/mem0 · 3,110 tokens

pydantic-ai AGENTS.md

AGENTS.md instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.

pydantic/pydantic-ai · 3,618 tokens

parlant CLAUDE.md

Instructions for emcie-co/parlant: This is the main repo of Parlant (https://parlant.io).

emcie-co/parlant · 611 tokens

redis-vl-python CLAUDE.md

Claude Code instructions for redis/redis-vl-python, covering claude.md - redisvl project context, frequently used commands, development workflow, redis setup and documentation.

redis/redis-vl-python · 1,033 tokens

dify AGENTS.md

AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.

langgenius/dify · 222 tokens

dify CLAUDE.md

Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

langgenius/dify · 3 tokens