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 cache-sweep-activation-fallbackgit 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/cache-sweep-activation-fallback)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/cache-sweep-activation-fallback"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-sweep-activation-fallback/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/cache-sweep-activation-fallback"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-sweep-activation-fallback.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 | $0.00456 |
| Opus 5.5 | $0.00012 | $0.00182 |
| Sonnet 5.5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
cache-sweep-activation-fallback 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: Cache Sweep Activation Fallback
Domain: extensions-mcp
Trigger: Apply when newly materialized extension sources must be activated immediately, but the live refresh can fail and needs a recoverable fallback.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
Treat installation and activation as separate phases. After a background reconcile changes what is on disk, clear the marketplace cache, attempt a full activation refresh, and degrade gracefully if that refresh throws. The fallback path should clear plugin caches again, log the failure, and set a sticky manual-refresh bit so the system admits that runtime state is stale instead of pretending activation succeeded.
Key Rules
- Only attempt automatic activation after a materialized change that needs live components to catch up; steady-state or metadata-only work should not enter this path.
- Clear upstream caches before activation so the refresh reads fresh marketplace and plugin state rather than replaying stale memoized data.
- Wrap the activation step in a catch boundary that logs the error and preserves the newly materialized state on disk.
- If activation fails, clear the plugin cache with a specific reason string and raise an idempotent manual-refresh flag instead of retrying blindly.
- Keep the fallback sticky until a deliberate refresh consumes it; repeated failures should not thrash the state tree with duplicate writes.
Example Application
If a background extension installer clones a new command marketplace during startup, clear the source cache, try a full runtime reload, and if the reload fails mark the UI with a single “reload extensions” prompt while preserving the newly cloned files for recovery.
Anti-Patterns (What NOT to do)
- Do not swallow activation failures after install; users will assume the new extension is live while the runtime still points at stale caches.
- Do not skip cache clearing before the activation attempt or the refresh may rehydrate old data and fail in harder-to-debug ways.
- Do not loop automatic retries without a user-visible fallback; repeated refresh crashes should turn into a manual recovery prompt.
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 ab5badd1901c
cache-sweep-activation-fallback 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 456 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.