agentmods.dev

drift CLAUDE.md

Project instructions for Fiberplane/Drift, a Zig command-line tool that checks whether Markdown documentation still matches the code. They describe the project's libraries, architecture, memory handling, and coding conventions.

In plain words
What is it for?
Use them when working on Drift's Zig code, documentation checks, tree-sitter parsing, Git integration, hashing, memory management, or command behavior.
Why use it?
They give an AI coding assistant the project-specific rules it needs to make consistent changes and avoid breaking established design choices.

Instructions file

139 2mo ago A scan 780 tokens original MIT
View the source file fiberplane/drift
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/fiberplane/drift/claude-md
Clone the repo
git clone --depth 1 https://github.com/fiberplane/drift
Per session 780 This file is loaded in full into every session.
When invoked 780 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.

ModelPer sessionOnce invoked
Fable 5 $0.00780 $0.00780
Opus 5 $0.00390 $0.00390
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 2d ago against content hash 4ba66701538e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drift 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 2d 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

@.fp/FP_CLAUDE.md

Stack

  • Language: Zig 0.16.0
  • C interop: tree-sitter (vendor/tree-sitter + vendor/zig-tree-sitter, parsed on demand)
  • Grammars: lazy zig build deps (not vendored)
  • CLI: zig-clap 0.11.0
  • VCS: shell out to git (jj support disabled until jj-native forges exist)
  • Hashing: std.hash.XxHash3 for content comparison

Architecture

drift binds markdown docs to code and lints for staleness. No daemon, no index, no cache. Every drift lint run is stateless: read docs, parse referenced files on demand, hash symbols, extract and check markdown links, query VCS, report.

Reference: docs/DESIGN.md, docs/DECISIONS.md, docs/CLI.md, docs/RELEASING.md

Zig Conventions

  • Two arenas per command: run_arena for command-lifetime data, scratch_arena for per-item temporaries (reset between iterations). GPA only in main(). See docs/DECISIONS.md §12.
  • Stack buffers for fixed-width formatting (fingerprint hex, small bufPrint targets)
  • Only OS/C resources get explicit deinit() — arena-backed data structs do not own memory
  • DebugAllocator in Debug builds for leak detection
  • File-is-the-struct pattern (Ghostty convention)
  • No anyerror in public APIs — explicit error sets
  • zig fmt enforced
  • Property tests use minish with deterministic seed overrides
  • All tests use std.testing.allocator

Code Patterns

  • Explicit error sets, no anyerror in public signatures
  • Tagged unions for VCS dispatch (Git | Jj)
  • Comptime string maps for language detection (extension → grammar)
  • Shell out for VCS operations via std.process.Child
  • Tree-sitter queries loaded from src/queries/<language>.scm at comptime

Adding a Language

  1. Add grammar dependency to build.zig.zon
  2. Add grammar compilation to build.zig grammars array
  3. Add extern declaration + extension mapping in src/parse/Language.zig
  4. Write src/queries/<language>.scm with symbol capture patterns
  5. Add test fixture

Markdown is a supported language with a two-grammar architecture: block grammar for document structure (section, atx_heading) and inline grammar for link extraction (inline_link). Both grammars are separate ts.Language instances compiled from tree-sitter-markdown.

Read the full file on GitHub · 71 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.

  1. 2d ago First seen · 71 lines · 780 tokens per session scan A 4ba66701538e

Subscribe to this mod's changes

drift CLAUDE.md is an instructions file published in the GitHub repository fiberplane/drift (139 stars, last pushed 2mo ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens