claude-grep: Instructions file for Claude Code

CLAUDE.md

claude-grep CLAUDE.md is an instructions file for Claude Code from evoleinik/claude-grep. It costs 649 tokens per session, scanned A, original, MIT.

A command-line search tool for finding text and meaning in Claude Code session history, the saved record of earlier conversations with the coding assistant.

In plain words
What is it for?
It helps search one or more projects by regular expression or meaning, filter for prompts, show nearby context, return JSON, and build or update a local search index.
Why use it?
It makes old prompts and answers easier to locate, including when the search uses related wording rather than the exact original words.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is evoleinik/claude-grep's own configuration. It tells Claude Code how to work on claude-grep itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-grep configures →

Reuse

Borrowing it

Nothing to install: this file belongs to evoleinik/claude-grep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/evoleinik/claude-grep/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/evoleinik/claude-grep

Made for: Claude Code.

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.

agentmods badge for claude-grep CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/evoleinik/claude-grep/claude-md.svg)](https://agentmods.dev/instructions/evoleinik/claude-grep/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/evoleinik/claude-grep/claude-md"><img src="https://agentmods.dev/badge/instructions/evoleinik/claude-grep/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 649 This file is loaded in full into every session.
When invoked 649 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00649 $0.00649
Opus 5 $0.00324 $0.00324
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 7d ago against content hash 9b37e16f33ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-grep 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 7d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-grep

Search Claude Code session history.

Quick reference

claude-grep "pattern"              # regex search
claude-grep -s "meaning query"     # semantic search
claude-grep --json "x" | jq .      # JSON output
claude-grep -p -C 2 "error"        # prompts only, with context
claude-grep -a -d 30 "deploy"      # all projects, 30 days
claude-grep --index                # build/update index
claude-grep --index --status       # index stats

Build

go build -o claude-grep .
go install .
go vet ./...

Architecture

File Purpose
main.go CLI flags, routing
search.go JSONL parsing, regex search, concurrent file processing
bm25.go BM25 query-focused paragraph compression
format.go Terminal (colored) and JSON output
index.go Ollama embedding, incremental indexer
store.go Gob-based vector store on disk
vector.go Cosine similarity, semantic search

Key design decisions

  • Zero dependencies (stdlib only + ollama HTTP API)
  • Pre-filter with bytes.Contains before JSON parse (10x faster)
  • Gob encoding for index (fast serialize/deserialize in Go)
  • Concurrent file search with fan-out/fan-in pattern
  • Semantic search threshold: cosine similarity > 0.3
  • BM25 compression: terminal output shows query-relevant chunks, not blind head truncation
  • Sentence-level splitting: large paragraphs broken into sentences for finer BM25 granularity
  • Stop word filtering + suffix stemming: deploy matches deployed/deploying/deployment
  • Adaptive budget: 15K total chars divided among matches (3 matches=2000 each, 50=300 each)
  • Cross-match content dedup: identical compressed text across sessions is collapsed
  • Near-miss hints: when regex finds nothing, extracts longest literal and does relaxed search to suggest simpler patterns
  • Auto-fallback: when regex finds 0 results and Ollama is running, automatically retries with semantic search
  • Short-pattern warning: patterns with longest literal ≤3 chars get a stderr hint to use -s instead
  • Self-exclusion: automatically skips the current session file (most recently modified within 60s) to avoid self-referential results
  • JSON output (--json) preserves full uncompressed text

Read the full file on GitHub · 65 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. 7d ago First seen · 65 lines · 649 tokens per session scan A 9b37e16f33ec

Subscribe to this mod's changes

claude-grep CLAUDE.md is an instructions file published in the GitHub repository evoleinik/claude-grep (2 stars, last pushed 3mo ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

next.js AGENTS.md

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

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 · 4,469 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

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