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-plugin-install-status-projectiongit 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-plugin-install-status-projection)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/nonblocking-plugin-install-status-projection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/nonblocking-plugin-install-status-projection/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-plugin-install-status-projection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/nonblocking-plugin-install-status-projection.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 | $0.00462 |
| Opus 5 | $0.00015 | $0.00231 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
nonblocking-plugin-install-status-projection 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 6d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Nonblocking Plugin Install Status Projection
Domain: extensions-mcp
Trigger: Use when marketplace reconciliation emits progress events but the main UI must remain responsive with up-to-date status rows.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
Before the async reconciliation runs, seed AppState with pending rows for every diffed marketplace. Pass a shared updater into the reconciler’s onProgress hook that maps each event type (installing, installed, failed) to the corresponding AppState entry by marketplace name, keeping the rest of the state untouched. When an event includes an error, annotate that marketplace row so the UI can reveal diagnostics while still letting other installers continue running.
Key Rules
- Always update AppState immutably via
setAppState(prev => ({ ...prev, plugins: { ...prev.plugins, installationStatus: { ... }}}))to avoid clobbering unrelated UI state. - Use a central helper like
updateMarketplaceStatusso each event only updates the matchingmarketplacesentry (by name) and nothing else. - Include event-specific metadata (
status, optionalerror) in the row so the UI can show spinners, success checks, or failure hints. - Keep this projection logic outside the main reconciling flow so the long-running
reconcileMarketplacescall never awaits UI updates; it merely fires events.
Example Application
If your agent tracks multiple plugin sources, apply this skill to emit nonblocking status rows for each install progress report so the user can monitor clones without stalling the command loop.
Anti-Patterns (What NOT to do)
- Do not mutate the AppState array in place or replace
installationStatuswholesale; that would drop other concurrent progress rows. - Do not ignore the
errorpayload on failures, or the UI will never explain why a marketplace install failed. - Avoid waiting for the entire reconciliation to finish before updating statuses; the whole point is incremental feedback.
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.
- 6d ago First seen · 29 lines · 30 tokens per session scan A 0b4a23280351
nonblocking-plugin-install-status-projection is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 462 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 2026-09-03.
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.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.