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 deferred-refresh-flag-contractgit 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/deferred-refresh-flag-contract)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/deferred-refresh-flag-contract"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/deferred-refresh-flag-contract/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/deferred-refresh-flag-contract"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/deferred-refresh-flag-contract.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 | $0.00037 | $0.00703 |
| Opus 5.5 | $0.00015 | $0.00281 |
| Sonnet 5.5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
deferred-refresh-flag-contract 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Deferred Refresh Flag Contract
Domain: extensions-mcp
Trigger: performBackgroundPluginInstallations completes reconcileMarketplaces and must decide whether to auto-refresh plugins or set plugins.needsRefresh via AppState.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
When new marketplaces are installed (result.installed.length > 0), treat the change as urgent: clear both marketplace and plugin caches, then call refreshActivePlugins(setAppState) so MCP connections re-establish with the freshly cloned sources. If that auto-refresh fails, log the error, clear the plugin cache with a reason string, and set plugins.needsRefresh = true so the UI prompts /reload-plugins. When only updates are available (result.updated.length > 0), do not auto-refresh; instead clear caches and set needsRefresh so the user opts into the reload. needsRefresh updates must be idempotent: the setter checks prev.plugins.needsRefresh and returns early if already true.
Key Rules
- Always run
clearMarketplacesCache()before refreshing or flagging; it ensures the cached metadata is rebuilt before the next plugin load. - For installs, wrap
refreshActivePlugins(setAppState)in a try/catch. On failure, callclearPluginCache('performBackgroundPluginInstallations: auto-refresh failed')and fall back to theneedsRefreshguard that sets the flag to true only once. - For updates-only, clear the plugin cache with
clearPluginCache('performBackgroundPluginInstallations: marketplaces reconciled')so stale plugin bundles are not re-used, but leave control in the user’s hands by settingneedsRefreshinstead of forcing a reload. - The
needsRefreshsetter usessetAppState(prev => { if (prev.plugins.needsRefresh) return prev; return { ...prev, plugins: { ...prev.plugins, needsRefresh: true } }; })so the UI can show a single prompt and avoid redundant re-renders.
Example Application
After reconcileMarketplaces returns result.installed = [ ... ], the manager clears caches and calls refreshActivePlugins. If the refresh completes, caches stay clear and MCP reconnects automatically. If the refresh throws, the catch logs the failure, clears the plugin cache with a descriptive reason, and the guard flips plugins.needsRefresh so /reload-plugins shows up instead. When only result.updated is populated, the same cache-clearing and guard runs, but without trying to refresh automatically.
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 · 29 lines · 37 tokens per session scan A 45e8dfc80e9b
deferred-refresh-flag-contract is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 703 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 2026-08-30.
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.