Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Reports what the watchmen plugin found in this workspace since its last curator run: new or changed skills, CLAUDE.md edits and a suggested skill to load.
Install Watchmen Brief
$ npx skills add firstbatchxyz/watchmen --skill brief -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install firstbatchxyz/watchmen brief --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/brief .claude/skills/brief && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .claude/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/briefType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add firstbatchxyz/watchmen --skill brief -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install firstbatchxyz/watchmen brief --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/brief .agents/skills/brief && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .agents/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add firstbatchxyz/watchmen --skill brief -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install firstbatchxyz/watchmen brief --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/brief .cursor/skills/brief && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .cursor/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/firstbatchxyz/watchmen.git --path plugin/skills/brief--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add firstbatchxyz/watchmen --skill brief -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install firstbatchxyz/watchmen brief --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/brief .gemini/skills/brief && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .gemini/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install firstbatchxyz/watchmen briefInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add firstbatchxyz/watchmen --skill brief -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/brief .github/skills/brief && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .github/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add firstbatchxyz/watchmen --skill brief -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install firstbatchxyz/watchmen brief --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/firstbatchxyz/watchmen.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/brief .opencode/skills/brief && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "brief" agent skill from https://github.com/firstbatchxyz/watchmen/tree/main/plugin/skills/brief into .opencode/skills/brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brief", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
brief- GitHub stars
- 297
- Token cost
- ~485 tokens
- SKILL.md length
- 260 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reports what the watchmen plugin found in this workspace since its last curator run: new or changed skills, CLAUDE.md edits and a suggested skill to load.
- Works in 4 steps: If the state says (no state) or (not a… → Otherwise, summarize in plain English… → If suggested_skill is non-null in the… → …
- Seeing the watchmen indicator in the status line and wanting to know what changed
- SKILL.md covers Current state for this workspace and What to do
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
When a watchmen indicator shows up in your status line, this skill prints the latest findings for the current workspace. It reads the JSON state that watchmen saved at the end of its last curator run, using the plugin's `read_state.sh`. If the state says there is none, or that the project is not tracked, the agent replies in one short sentence that nothing is new and stops.
Otherwise it summarizes in plain language, within three to five lines, which skills were added, updated or removed, whether CLAUDE.md changed and when. If the state names a suggested skill, the agent asks whether you want it for this session and, on a yes, tells you which slash command to run, since it cannot load skills itself. It ends with a one-line link to the side-by-side diff for that run, or to the project overview when no diff link exists. Reading the state also clears the status line indicator until the next run.
When your agent uses it
- Seeing the watchmen indicator in the status line and wanting to know what changed
- Checking whether CLAUDE.md or skills changed since the last curator run
- Deciding whether to load a skill that watchmen suggests for this session
Example prompts
- “Show me the watchmen brief for this project.”
- “What did watchmen find in this workspace?”
- “There is a lightbulb in my status line. What changed?”
Requirements
- The watchmen plugin installed, with its `read_state.sh` script
- Pre-approved tools (allowed-tools): Bash(*read_state.sh*)
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- If the state says (no state) or (not a tracked project): tell the user there's nothing new and stop. One short sentence.
- Otherwise, summarize in plain English what changed
- If suggested_skill is non-null in the state: ask the user "Want me to load the skill for this session?" and wait for a yes/no. If yes…
- Include a closing link to the run's details
What it can do on your machine
Read from SKILL.md and the folder at commit bbe763c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*read_state.sh*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Watchmen Brief loads about 485 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 260 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from firstbatchxyz/watchmen at commit bbe763c, republished under its MIT licence (© firstbatchxyz). 260 words, ~485 tokens.
Download SKILL.mdSave it as
.claude/skills/brief/SKILL.md (or your agent's skills folder).- name
- brief
- description
- Surface what watchmen detected in this workspace since the last curator run — new skills, CLAUDE.md changes, suggested actions to take this session.
- allowed-tools
- Bash(*read_state.sh*)
Watchmen brief
You are reporting watchmen's latest findings for the user's current workspace. The user invoked you because they saw a 💡 watchmen indicator in their statusLine and want to know what changed.
Current state for this workspace
The block below contains the JSON state file watchmen wrote at the end of its last curator run for this project. If it says (no state) or (not a tracked project), watchmen has nothing new to report.
!${CLAUDE_PLUGIN_ROOT}/bin/read_state.sh
What to do
If the state says
(no state)or(not a tracked project): tell the user there's nothing new and stop. One short sentence.Otherwise, summarize in plain English what changed:
- Which skills were added/updated/removed
- Whether CLAUDE.md changed
- When this happened (the
tsfield) - Keep it tight — 3-5 lines max. The user will ask for detail if they want it.
If
suggested_skillis non-null in the state: ask the user "Want me to load the<skill>skill for this session?" and wait for a yes/no. If yes, instruct them to invoke it (e.g./skill-name) — you can't load it programmatically, only signal.Include a closing link to the run's details:
- If
diff_urlis non-null (schema 2+): show that — it points at the side-by-side diff for this exact run, e.g.Diff: http://127.0.0.1:8979/p/kai-agent-new/diff/<sha> - Else fall back to
viewer_url(the project overview page) - One line, link only — no extra commentary.
- If
The read_state.sh call also touches an acknowledgment file, which clears the statusLine indicator for this project. So once you've shown the user this brief, the indicator will be gone until the next curator run.
© firstbatchxyz, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugin/skills/brief of firstbatchxyz/watchmen.
Open the folder on GitHubat commit bbe763c
Compare with similar skills
Watchmen Brief next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Watchmen Brief this skillfirstbatchxyz/watchmen | 297 | — | ~485 | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 102k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 | |
| Rules Distillationaffaan-m/ECC | 274k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Birdview Skills Compatibility AuditQiuner/birdview | 715 | — | ~794 | Automated safety check: Pass | MIT | |
| Context Routing Auditwithkynam/vibecode-pro-max-kit | 1.1k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
Rules Distillation
affaan-m/ECC
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
Birdview Skills Compatibility Audit
Qiuner/birdview
Audits the AI skills installed for a project for duplicate names, broad triggers and conflicting instructions, without changing any of them.
Context Routing Audit
withkynam/vibecode-pro-max-kit
Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report.
- Official
Mistral Vibe CLI Reference
mistralai/mistral-vibe
Reference for Mistral Vibe, the CLI agent it runs inside: config files, env vars, agents, skills, tools, hooks and MCP servers, so the agent can explain and troubleshoot its own setup.
More from firstbatchxyz/watchmen
Watchmen Setup
firstbatchxyz/watchmen
Walks through installing watchmen, running its init wizard, wiring the plugin into Codex or Claude Code and checking the result with doctor.
Watchmen Setup
firstbatchxyz/watchmen
Sets up watchmen on the current machine: installs the CLI, hands off the init wizard, wires the plugin and statusline into Claude Code and Codex, and verifies with doctor.
Watchmen Workspace Brief
firstbatchxyz/watchmen
Summarizes what the watchmen tool detected in your workspace since its last curator run: skill changes, AGENTS.md edits and a suggested skill to load.
Related
Categories
Questions about Watchmen Brief
What does Watchmen Brief do?
Reports what the watchmen plugin found in this workspace since its last curator run: new or changed skills, CLAUDE.md edits and a suggested skill to load. When a watchmen indicator shows up in your status line, this skill prints the latest findings for the current workspace.sh`.
When should I use Watchmen Brief?
Watchmen Brief fits situations like: seeing the watchmen indicator in the status line and wanting to know what changed; checking whether CLAUDE.md or skills changed since the last curator run; deciding whether to load a skill that watchmen suggests for this session.
How do I install Watchmen Brief in Claude Code?
Run `npx skills add firstbatchxyz/watchmen --skill brief -a claude-code`. Or copy the skill folder (plugin/skills/brief in firstbatchxyz/watchmen) into .claude/skills/brief in your project. Claude Code loads it when a task matches its description.
How do I install Watchmen Brief in Codex?
Run `npx skills add firstbatchxyz/watchmen --skill brief -a codex`. Or copy the skill folder (plugin/skills/brief in firstbatchxyz/watchmen) into .agents/skills/brief in your project. Codex loads it when a task matches its description.
Can I use Watchmen Brief in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add firstbatchxyz/watchmen --skill brief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brief, .gemini/skills/brief, .github/skills/brief and .opencode/skills/brief in your project.
What does Watchmen Brief need to run?
SKILL.md names no scripts, command-line tools or credentials: Watchmen Brief is instructions for the agent only. Our summary lists: The watchmen plugin installed, with its `read_state.sh` script. Its frontmatter pre-approves these tools: Bash(*read_state.sh*).
Does Watchmen Brief access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Watchmen Brief safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Watchmen Brief use?
Watchmen Brief is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Watchmen Brief use?
About 485 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Watchmen Brief?
Skills that share tags, products or a category with Watchmen Brief: Using Agent Skills (addyosmani/agent-skills, 102k stars), Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars), Rules Distillation (affaan-m/ECC, 274k stars) and Birdview Skills Compatibility Audit (Qiuner/birdview, 715 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Watchmen Brief?
firstbatchxyz (a GitHub organization) maintains it in firstbatchxyz/watchmen, which has 297 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 25, 2026.
Source: firstbatchxyz/watchmen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.