tagit: Instructions file for Claude Code

CLAUDE.md

tagit CLAUDE.md is an instructions file for Claude Code from liliang-cn/tagit. It costs 2,045 tokens per session, scanned C, original, MIT.

Repository instructions for TagIt, a tool that runs interactive coding-agent command-line programs through one control system. They describe how to build, test, run, and understand its Go code.

In plain words
What is it for?
Building and testing TagIt, running focused Go tests, checking concurrent code for race conditions, and navigating its daemon-first architecture.
Why use it?
They prevent workspace settings from affecting builds and tests, and make the required race checks clear. They also explain where the daemon, runtime, and other modules fit.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is liliang-cn/tagit's own configuration. It tells Claude Code how to work on tagit 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 tagit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to liliang-cn/tagit. 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/liliang-cn/tagit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/liliang-cn/tagit

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 tagit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/liliang-cn/tagit/claude-md/github.svg)](https://agentmods.dev/instructions/liliang-cn/tagit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/liliang-cn/tagit/claude-md"><img src="https://agentmods.dev/badge/instructions/liliang-cn/tagit/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tagit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/liliang-cn/tagit/claude-md"><img src="https://agentmods.dev/badge/instructions/liliang-cn/tagit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,045 This file is loaded in full into every session.
When invoked 2,045 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02045 $0.02045
Opus 5 $0.01022 $0.01022
Sonnet 5 $0.00409 $0.00409
Haiku 4.5 $0.00204 $0.00204

Measured 9d ago against content hash ac1e53ab8be8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

tagit CLAUDE.md scanned grade C with 1 finding 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 9d 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.

Nullifies safety policieshighAnti-refusal

"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.

- `mcpserver` — exposes TagIt to other agents over MCP (`tagit mcp`, stdio). A thin facade over the `api` client built on `github.com/modelcontextprotocol/go-sdk`: every tool is a call the CLI could already make, so the
CLAUDE.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build, Test, Run

The Makefile sets GOWORK=off; reuse it instead of invoking go bare so workspace files in parent directories don't pollute the build.

make build        # builds bin/tagit, bin/tagitd
make test         # GOWORK=off go test -count=1 ./...
make install      # installs the two binaries to $HOME/.local/bin

Single-package or single-test iteration (mirror the env the Makefile uses):

GOWORK=off go test ./internal/runtime/...
GOWORK=off go test -run TestSupervisorStart ./internal/runtime
GOWORK=off go test -race -count=1 ./...   # what CI runs

CI (.github/workflows/ci.yml) runs go build ./... and go test -race -count=1 ./... on Ubuntu and macOS. The -race flag matters: PTY/runtime/scheduler code spawns goroutines and races usually only show up with it on.

Big Picture

TagIt is a daemon-first orchestrator that runs interactive coding-agent CLIs (claude, codex, gemini, ...) under a single control plane. Two binaries:

  • cmd/tagitd — kernel daemon. A 28-line main.go that just wires internal/app.Daemon with signal handling and an optional --acp-port.
  • cmd/tagit — CLI client. cmd/tagit/main.go is a single ~4000-line dispatcher: run() switches on the first arg into runRun, runQueue, runAgents, runDebug, etc. Most commands talk to tagitd via the API server in internal/api; some inspection commands open the SQLite store directly.

Source-of-truth rule (from DESIGN.md §3 and docs/backend-module-design.md §1, §8): business state lives in the persisted event/store, not in runtime memory. Allowed in-memory state is limited to runtime handle registries, classifier buffers, scheduler work queues. Anything orchestration-shaped (session/task lifecycle, accepted artifacts, approvals) must round-trip through internal/store.

Module layout under internal/

The package layout in internal/ follows docs/backend-module-design.md §10. Dependency direction is strictly enforced and acyclic; before adding an import, check the rules in that doc:

Read the full file on GitHub · 107 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. 9d ago First seen · 107 lines · 2,045 tokens per session scan C ac1e53ab8be8

Subscribe to this mod's changes

tagit CLAUDE.md is an instructions file published in the GitHub repository liliang-cn/tagit (5 stars, last pushed 4d ago), licensed MIT. It adds 2,045 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it C with 1 finding (nullifies safety policies). 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

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

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 · 5,153 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens