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/mlops-kelvin/github-channels/configurenpx skills add mlops-kelvin/github-channels --skill configuregit clone --depth 1 https://github.com/mlops-kelvin/github-channelsWrote 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/mlops-kelvin/github-channels/configure)<a href="https://agentmods.dev/skills/mlops-kelvin/github-channels/configure"><img src="https://agentmods.dev/badge/skills/mlops-kelvin/github-channels/configure.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 | $0.00023 | $0.01938 |
| Opus 5 | $0.00012 | $0.00969 |
| Sonnet 5 | $0.00005 | $0.00388 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade E, and why
configure scanned grade E with 4 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST https://your-domain.com/webhook -H "Content-Type: application/json" -d '{}' Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
After adding, reload: `sudo systemctl reload angie` or `sudo nginx -s reload` 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.
curl -sf http://127.0.0.1:8789/status | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"channel_tip": "Tip: curl -X POST localhost:8789/mute/owner/repo?hours=5 to mute a noisy repo.", How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
github-channels Configuration
Complete setup and configuration reference for the github-channels plugin.
Prerequisites
- Bun runtime installed
- Reverse proxy (Angie, nginx, Caddy) forwarding
/webhooktolocalhost:PORT - GitHub admin access on repos you want to monitor (for webhook creation)
Config File
Location: ~/.claude/channels/github-channels/config.json
Created automatically on first run. Edit to configure:
{
"port": 8789,
"host": "127.0.0.1",
"repos": ["owner/repo-a", "owner/repo-b"],
"events": ["push", "pull_request", "issues", "issue_comment", "pull_request_review"],
"trusted_actors": ["username1", "username2"],
"channel_tip": "Tip: curl -X POST localhost:8789/mute/owner/repo?hours=5 to mute a noisy repo.",
"muted": false
}
Field Reference
| Field | Type | Default | Description |
|---|---|---|---|
port |
number | 8789 |
HTTP listener port for webhooks |
host |
string | "127.0.0.1" |
Bind address (always localhost) |
repos |
string[] | [] |
GitHub repos to accept webhooks from (owner/repo format). Empty = reject all. |
events |
string[] | 5 defaults | Event types to forward. Options: push, pull_request, issues, issue_comment, pull_request_review, check_run, workflow_run, release |
trusted_actors |
string[] | [] |
GitHub usernames. Events from these users get trust_tier=team. Everyone else gets trust_tier=external. |
channel_tip |
string | "" |
Text appended to every channel event (reminders, mute commands) |
muted |
boolean | false |
Start muted (no events delivered until unmuted) |
Config Changes Require Restart
Editing config.json requires restarting Claude Code. The config is read once at server startup.
Mute/unmute is hot — no restart needed (uses HTTP control endpoints).
Webhook Secret
Location: ~/.github-channels-secret
Auto-generated on first run (40-char hex, file mode 600). To view:
cat ~/.github-channels-secret
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.
- 3d ago First seen · 196 lines · 23 tokens per session scan E e711f64a4944
configure is a skill published in the GitHub repository mlops-kelvin/github-channels (0 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,938 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 4 findings (sends data to an external url, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…