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 skills add ychampion/cskill-agents --skill nonblocking-post-connect-capability-broadcastgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/nonblocking-post-connect-capability-broadcast)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/nonblocking-post-connect-capability-broadcast"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/nonblocking-post-connect-capability-broadcast/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/nonblocking-post-connect-capability-broadcast"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/nonblocking-post-connect-capability-broadcast.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00544 |
| Opus 5.5 | $0.00012 | $0.00218 |
| Sonnet 5.5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
nonblocking-post-connect-capability-broadcast 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 1mo 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Nonblocking Post-Connect Capability Broadcast
Domain: bridge-lifecycle Trigger: Apply when a transport has reached its ready or connected state, but optional capability discovery and hello metadata still need to be broadcast to the remote peer. Source Pattern: Distilled from reviewed bridge-lifecycle, capability-broadcast, and reconnect-flow implementations.
Core Method
Treat connection visibility and capability advertisement as two separate phases. In the state-change handler, synchronously commit the host's connected/session-active flags first so the UI and downstream effects can react immediately. Only after that state commit should you launch a detached async task that resolves optional capabilities, re-checks cancellation or liveness, snapshots any current state needed for the payload, and sends the post-connect broadcast. Keep the late path best-effort: if capability loading or broadcast assembly fails, log it locally and leave the connection marked ready.
Key Rules
- Commit the connected or session-active state before awaiting any optional capability load; readiness must not depend on slow skill or metadata discovery.
- Run the post-connect broadcast in fire-and-forget async work guarded by a local
try/catchso failures do not bubble back into the connection transition. - Re-check cancellation or handle liveness after the awaited capability work and before writing to the transport; the peer may already be gone.
- Read mutable payload state as late as practical inside the async task so the broadcast reflects the current permission mode, agents, or feature flags rather than a stale pre-await snapshot.
- Keep the broadcast path optional and feature-gated when the metadata is additive rather than required for connection correctness.
Example Application
When a mobile or web client connects to a background bridge, flip the app state to connected immediately so forwarding and UI badges start right away. Then, in a detached async block, load the bridge-safe skill list, collect the latest runtime metadata, and send one system/init message. If that late load fails, record the error, but do not bounce the session back out of connected.
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.
- 1mo ago First seen · 30 lines · 30 tokens per session scan A 515863335ea1
nonblocking-post-connect-capability-broadcast is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 544 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.