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/tkellogg/open-strix/github-pollernpx skills add tkellogg/open-strix --skill github-pollergit clone --depth 1 https://github.com/tkellogg/open-strixWhat 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 | $0.00050 | $0.00589 |
| Opus 5 | $0.00025 | $0.00295 |
| Sonnet 5 | $0.00010 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
github-poller 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 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Repository Poller
Monitors GitHub repositories for new activity. Emits events to the agent only when there's something actionable.
Installation
Install from ClawHub:
npx clawhub install github-poller
Or copy this skill directory into your agent's skills/ folder.
After installation, call reload_pollers to register the poller with the scheduler.
Setup
1. Set environment variables
The poller reads credentials from the agent's environment (.env file or system env):
| Variable | Required | Description |
|---|---|---|
GITHUB_TOKEN |
yes | GitHub personal access token or gh CLI token |
GITHUB_REPOS |
yes | Comma-separated list of repos to monitor (e.g., owner/repo1,owner/repo2) |
Note: The gh CLI auth token works if gh is installed and authenticated. The poller tries gh auth token as a fallback if GITHUB_TOKEN isn't set.
2. Configure pollers.json
The skill ships with a default pollers.json that polls every 15 minutes:
{
"pollers": [
{
"name": "github-activity",
"command": "python poller.py",
"cron": "*/15 * * * *"
}
]
}
Adjust the cron schedule as needed. For active repos, */5 * * * * works but watch API rate limits.
3. Reload pollers
After installation, call reload_pollers to register the poller with the scheduler.
What It Reports
The poller emits events for:
- New issues opened on your repos
- New pull requests opened on your repos
- New comments on issues and PRs (excluding your own bot account)
- PR reviews submitted (excluding your own)
Each event includes the repo, author, title/body, and URLs needed to act.
Filtering
- Comments and reviews from the authenticated account are excluded (avoids self-notification loops)
- Only activity since the last successful poll is reported
- Empty polls produce no output (silence = nothing new)
Dependencies
Requires either:
- The
ghCLI installed and authenticated, OR - A
GITHUB_TOKENenvironment variable with repo read access
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 80 lines · 50 tokens per session scan A 427949c733ca
github-poller is a skill published in the GitHub repository tkellogg/open-strix (84 stars, last pushed 28d ago), licensed MIT. It adds 50 tokens to every session and 589 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…