What is lgrep AGENTS.md?

Project instructions for lgrep, a local tool that searches code by meaning and finds symbols, callers, and affected code. They also define how to prepare a worktree, an isolated working copy of a repository.

Use them to initialise a worktree, set up lgrep's isolated files and dependencies, find relevant code, check types, and run tests.

They provide a consistent setup and search process so developers can explore an unfamiliar codebase with the right environment and context.

lgrep AGENTS.md — Instructions file by dennisonbertram

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/dennisonbertram/lgrep/agents-md

Clone the repo

git clone --depth 1 https://github.com/dennisonbertram/lgrep

Made for: Codex, OpenCode.

Per session 1,561 This file is loaded in full into every session.

When invoked 1,561 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	$0.01561	$0.01561
Opus 5	$0.00781	$0.00781
Sonnet 5	$0.00312	$0.00312
Haiku 4.5	$0.00156	$0.00156

Measured 2d ago against content hash 92f0d8f2307f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lgrep 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 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.

AGENTS.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Configuration

Worktree Bootstrap

Run this first in every new shell and every new worktree:

source ./init.sh

init.sh is the canonical repo bootstrap. It keeps setup simple and zero-dependency beyond the normal git + node + npm toolchain that this project already needs.

What it does:

Verifies Node.js >= 18.17.
Sets LGREP_HOME to .worktree/lgrep inside the current worktree so watchers, config, cache, and indexes stay isolated per worktree.
Reuses a shared npm install stored under the git common directory, keyed by the lockfile, platform, architecture, and exact Node version.
Uses a lock directory so multiple worktrees can bootstrap in parallel safely.
Adds ./node_modules/.bin to PATH for the current shell.

Recommended flow:

source ./init.sh
npm run type-check
npm test

Prefer source ./init.sh over ./init.sh. If you execute it directly, it will prepare the environment files but cannot export variables back into your current shell.

lgrep - Local Semantic Code Search

Use lgrep first for code exploration, context building, symbol lookup, callers, impact, and semantic search.

Hard Rule

Prefer lgrep over grep, rg, or manual file-by-file inspection whenever you are trying to understand the codebase.
Only reach for rg or grep first when you already know the exact literal string, filename, or regex you need.
If a hosted lgrep server is configured, assume it is the default source of truth for project/worktree-aware reads unless you explicitly need a local-only index.
When working inside a git worktree, let lgrep auto-detect the hosted project/worktree first before adding manual --project or --worktree flags.

When to Use

Searching for code by meaning
Understanding how the codebase works
Building context for implementing features
Finding where functionality is implemented
Locating relevant files for a task
Diagnosing configuration issues

Quick Commands

Read the full file on GitHub · 171 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.

2d ago First seen · 171 lines · 1,561 tokens per session scan A 92f0d8f2307f

Subscribe to this mod's changes

lgrep AGENTS.md is an instructions file published in the GitHub repository dennisonbertram/lgrep (88 stars, last pushed 2mo ago), licensed MIT. It adds 1,561 tokens to every session, about $0.0078 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.

Git and workflow Testing Writing and docs

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

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

lgrep AGENTS.md