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.
npx agentmods add skills/justincampbell/gh-watch/watch-commitnpx skills add justincampbell/gh-watch --skill watch-commitgit clone --depth 1 https://github.com/justincampbell/gh-watchWrote 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.
[](https://agentmods.dev/skills/justincampbell/gh-watch/watch-commit)<a href="https://agentmods.dev/skills/justincampbell/gh-watch/watch-commit"><img src="https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-commit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.00739 |
| Opus 5 | $0.00024 | $0.00369 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
watch-commit 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch a Commit
Monitor a commit's CI checks for state changes using the gh watch CLI extension. It polls GitHub and emits one JSON event per line to stdout, which makes it a natural fit for the Monitor tool — each event arrives in the conversation as a notification. Exits automatically when all checks complete.
Prerequisites
Check if the extension is installed:
gh watch --help
If not installed:
gh extension install justincampbell/gh-watch
Usage
Run with the Monitor tool (not Bash with run_in_background). The first notification is the initial-state snapshot; the next is the terminal ci-passed or ci-failed, after which gh-watch exits.
Watch a commit by SHA (current repo):
command:gh watch commit $ARGUMENTSdescription:Commit $ARGUMENTS CI statuspersistent:falsetimeout_ms:1800000(30 min — raise for slow CI)
Watch a commit by GitHub URL:
command:gh watch commit https://github.com/owner/repo/commit/abc1234
Exit only if CI passes (use --exit-on to ignore failures):
command:gh watch commit $ARGUMENTS --exit-on ci-passed
Flags
| Flag | Description | Default |
|---|---|---|
--interval <duration> |
Polling interval | 60s |
--exit |
Exit after any state change | false |
--exit-on <events> |
Exit after specific event types (comma-separated) |
Event types
| Event | Description |
|---|---|
initial-state |
Snapshot of commit CI state at the moment watching started (always emitted first) |
ci-passed |
All CI checks passed (terminal — always exits) |
ci-failed |
CI failed (at least one check failed) (terminal — always exits) |
Output format
One JSON object per line on stdout. The first line is always initial-state — a snapshot of the commit's CI at the moment watching began:
{"timestamp":"...","event":"initial-state","summary":"Commit abc1234: Message — CI: 3/5 passed, 2 pending","details":{"sha":"abc1234...","checks":5,"passed":3,"failed":0,"pending":2}}
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.
- 4d ago First seen · 81 lines · 48 tokens per session scan A 7248ed4cf6e0
watch-commit is a skill published in the GitHub repository justincampbell/gh-watch (4 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 739 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
claudeconf
Set up or harden a project's quality and security pipeline — git hooks, CI, tests, and pre-merge gates. Researches and pins tools that fit the project's stack instead of using fixed choices, then wires a standard-tool harness you own. Use when initializing a repo, adding CI or pre-commit checks, hardening an existing…
GitHub Actions Workflow Security Review
Reviews GitHub Actions workflow diffs for script injection of untrusted input, pullrequesttarget with untrusted checkout, over-broad GITHUBTOKEN permissions, and unpinned third-party actions.
developer-code-organization
Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.
developer-internals
Internal gh-aw architecture: validation system design, safe output message patterns, schema validation, YAML compatibility notes, and MCP logs guardrail.
developer-release
Release management, changeset workflow, firewall log parsing, breaking CLI change rules, and Go module summaries for gh-aw.
github-mcp-server
Reference for GitHub MCP server tools, methods, and usage patterns.