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 auto-refresh-after-new-plugin-sourcesgit 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/auto-refresh-after-new-plugin-sources)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/auto-refresh-after-new-plugin-sources"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/auto-refresh-after-new-plugin-sources/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/auto-refresh-after-new-plugin-sources"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/auto-refresh-after-new-plugin-sources.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 | $0.00025 | $0.00406 |
| Opus 5.5 | $0.00010 | $0.00162 |
| Sonnet 5.5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
auto-refresh-after-new-plugin-sources 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.
What it actually says
SKILL: Auto Refresh After New Plugin Sources
Domain: tool-orchestration Trigger: Apply when background reconciliation installs at least one new marketplace and the agent must refresh plugin cache without explicit user action. Source Pattern: Distilled from reviewed post-install refresh and extension-cache invalidation implementations.
Core Method
After reconciliation reports at least one newly installed plugin source, clear both the source cache and the active plugin cache, then trigger a refresh of the live extension registry. Treat that refresh as best-effort but important: if it succeeds, the new tools become available immediately; if it fails, log the error and raise a manual-refresh flag so the user sees that recovery is required. Do this before treating downstream extension operations as ready, otherwise the product will keep resolving against stale code.
Key Rules
- Only trigger the refresh when new installs occurred; avoid redundant refresh cycles after mere updates.
- Clear both marketplace and plugin caches before refreshing to ensure stale data cannot leak into the newly loaded plugins.
- Catch refresh failures, log the error, and set a visible manual-refresh flag rather than silently failing.
- Keep analytics/logging tied to the install path so you know when an automatic refresh runs and whether it failed or succeeded.
Example Application
If a new marketplace is added via a curated list, automatic refresh ensures CLI commands that rely on that marketplace can resolve tools without forcing users to manually run a separate reload step.
Anti-Patterns (What NOT to do)
- Do not refresh plugin state when there are zero new installs; the extra cache clears slow startup without benefit.
- Do not swallow refresh errors; otherwise users never learn the auto recovery failed and manual action stays hidden.
- Do not reuse stale caches while refreshing; skip clearing caches then refresh and the agent continues pointing at old code.
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 · 31 lines · 25 tokens per session scan A b307ce535b07
auto-refresh-after-new-plugin-sources is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 406 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.