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 materialization-aware-refresh-escalationgit 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/materialization-aware-refresh-escalation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/materialization-aware-refresh-escalation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/materialization-aware-refresh-escalation.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00702 |
| Opus 5 | $0.00017 | $0.00351 |
| Sonnet 5 | $0.00007 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
materialization-aware-refresh-escalation 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 4d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Materialization-Aware Refresh Escalation
Domain: extensions-mcp
Trigger: When background plugin installation reconcilers detect that declared marketplaces differ from what is materialized, use the diff to decide whether to auto-refresh plugins or escalate to a manual refresh prompt.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
- Before reconciling, read the declared marketplaces (
getDeclaredMarketplaces()), the previously materialized config (loadKnownMarketplacesConfig()), and computediffMarketplaces()so you know which names are missing or changed. - Build
pendingNamesfromdiff.missingplusdiff.sourceChangedso the UI reports exactly which marketplaces are still being processed; return early when that array is empty so no work runs unless there is material change. - Call
reconcileMarketplaces({ onProgress }), map theinstalling/installed/failedevents to AppState, track metrics for installed/updated/failed/up-to-date counts, and log them vialogEventand diagnostics helpers. - After reconciliation, inspect the result:
- When
result.installed.length > 0, clear the marketplace cache, log the auto-refresh path, and awaitrefreshActivePlugins(setAppState)inside a try/catch so MCP caches are rebuilt. On refresh failure, log the error, clear the plugin cache, and setplugins.needsRefreshvia AppState only if it was previously false. - When there are no fresh installs but
result.updated.length > 0, clear both marketplace and plugin caches and set theneedsRefreshflag so the UI invites/reload-pluginswhile avoiding an automatic refresh. - When there are neither installs nor updates, skip cache invalidation and refresh so the reconciliation stays lightweight.
- When
Key Rules
- Only auto-refresh when brand-new marketplaces were installed; updates-only reconciliations should not trigger the refresh path.
- Clear both marketplace and plugin caches before touching
refreshActivePluginsor settingneedsRefreshso stale artifacts cannot leak into the new plugin state. - Always wrap
refreshActivePluginsin a try/catch, log failures (logError,logForDebugging), and fall back toneedsRefreshrather than silently suppressing the error. - Guard the
needsRefreshsetter so it only flips once per failure path and never reassigns while the flag is already true.
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.
- 4d ago First seen · 35 lines · 34 tokens per session scan A 06d4eb886383
materialization-aware-refresh-escalation is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 702 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.
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
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.