pulse

pulse is a skill for Claude Code, Codex from fakoli/fakoli-plugins. It costs 129 tokens per session (1,394 once invoked), scanned B, original, MIT.

A local dashboard for watching long-running Anvil projects. It shows active work claims, elapsed time, lease countdowns, recent events, and signs that a run may be stuck.

In plain words
What is it for?
Use it to watch an Anvil run, inspect its event feed, check whether work is healthy or quiet, and spot expired leases or possibly wedged tasks.
Why use it?
It lets you monitor autonomous work in a browser without repeatedly checking command-line output or changing the project's stored state.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the anvil-pulse plugin — 1 skill, 1 command shipped together

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/fakoli/fakoli-plugins/pulse
Any agent
npx skills add fakoli/fakoli-plugins --skill pulse
Clone the repo
git clone --depth 1 https://github.com/fakoli/fakoli-plugins

Made for: Claude Code, Codex.

Or install anvil-pulse, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 pulse

README.md
[![agentmods](https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/pulse.svg)](https://agentmods.dev/skills/fakoli/fakoli-plugins/pulse)
Your own site
<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/pulse"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/pulse.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,394 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00129 $0.01394
Opus 5 $0.00064 $0.00697
Sonnet 5 $0.00026 $0.00279
Haiku 4.5 $0.00013 $0.00139

Measured 3d ago against content hash 93f86243244d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

pulse scanned grade B 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. Read `~/.claude/settings.json` -> `statusLine.command` to find the script

Makes network callslowCapability

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

`curl -s http://localhost:<port>/api/pulse`
plugins/anvil-pulse/skills/pulse/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

anvil pulse

A local operator dashboard for anvil projects. It polls anvil status --json and tails the append-only events.jsonl, then serves a single self-contained web page. It never writes anvil state.

Toolkit (bundled)

${CLAUDE_PLUGIN_ROOT}/scripts/start-server.sh   # start (prints {"event":"server-started","url":...})
${CLAUDE_PLUGIN_ROOT}/scripts/stop-server.sh    # stop
${CLAUDE_PLUGIN_ROOT}/scripts/check-server.sh   # is it running?
${CLAUDE_PLUGIN_ROOT}/scripts/statusline-segment.sh  # optional Claude Code statusline segment

All scripts take --project-dir <path> (default: cwd). Requires node and the anvil CLI on PATH.

Start the dashboard

  1. Confirm the target project is anvil-initialized: anvil status --json --cwd <project> exits 0. If not, tell the user and stop — the dashboard has nothing to show.
  2. Run:
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/start-server.sh" --project-dir <project>
    
  3. Parse the JSON line and give the user the url. Suggest opening it in a browser; it live-updates every ~2.5s.
  4. On Windows/Git Bash and Codex the script auto-runs in the foreground (detached processes get reaped there). In that case start it with the shell tool's background/run-in-background mode so it survives the turn, or tell the user to run it in a separate terminal: bash .../start-server.sh --project-dir <project> --foreground

Options worth knowing: --port <n> for a stable URL, --state-dir <dir> if anvil state lives in a non-default workspace dir (auto-discovery checks <project>/.anvil, <project>/bin/.anvil, then the most recently modified ~/.anvil/workspaces/*/events.jsonl — a warning banner on the page reports which one it picked).

Suggest adding .anvil-pulse/ to the project's .gitignore (pid/log files live there).

Stop / check

bash "${CLAUDE_PLUGIN_ROOT}/scripts/stop-server.sh"  --project-dir <project>
bash "${CLAUDE_PLUGIN_ROOT}/scripts/check-server.sh" --project-dir <project>

Read the full file on GitHub · 108 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. 3d ago First seen · 108 lines · 129 tokens per session scan B 93f86243244d

Subscribe to this mod's changes

pulse is a skill published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 25d ago), licensed MIT. It adds 129 tokens to every session and 1,394 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

better-auth-knowledge-patch

Use this skill when implementing, upgrading, debugging, or reviewing Better Auth applications. Start with the quick references below, then load the topic file that matches the task.

Nevaberry/nevaberry-plugins · 9 tokens

clickhouse-knowledge-patch

Use this skill when writing, reviewing, upgrading, or operating ClickHouse SQL and server configurations. Start with the compatibility-sensitive items below, then load the topic reference that matches the task.

Nevaberry/nevaberry-plugins · 9 tokens

arch-knowledge-patch

Restart the daemon immediately after upgrading openssh to 9.8p1 because the old daemon cannot accept new connections.

Nevaberry/nevaberry-plugins · 8 tokens

axum-knowledge-patch

Axum 0.8 uses return-position impl Trait in FromRequestParts and FromRequest. Implement their methods with native async fn; do not retain the old #[asynctrait] annotation.

Nevaberry/nevaberry-plugins · 9 tokens

caddy-knowledge-patch

Use this patch when writing or reviewing Caddyfile or JSON configuration, upgrading Caddy, building custom binaries, or operating Caddy's HTTP, proxy, certificate, and telemetry features.

Nevaberry/nevaberry-plugins · 9 tokens

cloudflare-d1-knowledge-patch

Use this skill when designing, implementing, migrating, operating, or debugging Cloudflare D1 databases. Check the project’s Wrangler configuration, binding usage, database generation, account plan, and remote-versus-local command flags before applying guidance.

Nevaberry/nevaberry-plugins · 13 tokens