setup

A setup guide for watchmen, a local command-line tool that turns past coding-agent sessions into a curated library of reusable skills. It explains how to install and connect watchmen to Codex and Claude Code.

In plain words
What is it for?
Use it to install watchmen, run its initialization wizard, connect it to coding agents, and verify the installation with its diagnostic command.
Why use it?
It removes the manual work of installing the tool, running its setup, and checking whether the connection works. It also keeps provider credentials in the setup wizard rather than exposing them to the agent.

Skill for Claude CodeCodex

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 skills/firstbatchxyz/watchmen/setup
Any agent
npx skills add firstbatchxyz/watchmen --skill setup
Clone the repo
git clone --depth 1 https://github.com/firstbatchxyz/watchmen

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00059 $0.01096
Opus 5 $0.00030 $0.00548
Sonnet 5 $0.00012 $0.00219
Haiku 4.5 $0.00006 $0.00110

Measured 2d ago against content hash ed043e62d0c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

setup scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **`uv: MISSING`** → stop and tell the user to install uv first (`curl -LsSf https://astral.sh/uv/install.sh | sh`, or `brew install uv`), then re-run this skill. uv is the only hard prerequisite besides a provider cred

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`uv: MISSING`** → stop and tell the user to install uv first (`curl -LsSf https://astral.sh/uv/install.sh | sh`, or `brew install uv`), then re-run this skill. uv is the only hard prerequisite besides a provider cred
plugin-codex/skills/setup/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up watchmen

You are guiding the user through installing and wiring watchmen on this machine. watchmen is a local CLI that turns past coding-agent sessions into a curated skills library and surfaces it back into new sessions. This skill is a thin orchestrator: you run the non-interactive shell steps yourself, and for the steps that are interactive (the init wizard) or that only the agent UI can do (plugin install), you give the user the exact commands and wait.

Do not touch the user's API keys or credentials directly — the init wizard handles provider auth. Never paste a key on the user's behalf.

Before you start

Check what's already here so you don't redo work:

!uname -s; command -v uv >/dev/null && echo "uv: $(uv --version)" || echo "uv: MISSING"; command -v watchmen >/dev/null && echo "watchmen: $(watchmen --version 2>/dev/null)" || echo "watchmen: not installed"

Read that output and branch:

  • uv: MISSING → stop and tell the user to install uv first (curl -LsSf https://astral.sh/uv/install.sh | sh, or brew install uv), then re-run this skill. uv is the only hard prerequisite besides a provider credential.
  • watchmen already installed → skip to step 3 (verify) and only fix what doctor flags. Don't reinstall over a working setup.
  • Fresh machine → walk steps 1 → 4 in order.

1. Install the CLI

watchmen installs as an editable uv tool from a clone, so git pull + the daemon pick up updates:

git clone https://github.com/firstbatchxyz/watchmen.git
cd watchmen
uv sync && uv tool install --editable .

Run these for the user (pick a sensible parent dir, or ask where they want the clone). If the clone already exists, cd into it and just run the uv sync && uv tool install --editable . line.

2. Run the init wizard (interactive — hand off)

watchmen init is an interactive wizard: it asks which LLM provider to use (OpenRouter / OpenAI / Anthropic, or an OAuth subscription on macOS), prompts for that provider's API key, ingests ~/.claude/projects/ history, lets the user pick projects, previews cost, runs analyze + curate, and installs the daemon + viewer for autostart.

Read the full file on GitHub · 87 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 · 87 lines · 59 tokens per session scan C ed043e62d0c2

Subscribe to this mod's changes

setup is a skill published in the GitHub repository firstbatchxyz/watchmen (295 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 1,096 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens