Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kvdm-co-pilot/create-cmpnpx agentmods add skills/kvdm-co-pilot/create-cmp/plugin-refreshWrote 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/kvdm-co-pilot/create-cmp/plugin-refresh)<a href="https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/plugin-refresh"><img src="https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/plugin-refresh/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/kvdm-co-pilot/create-cmp/plugin-refresh"><img src="https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/plugin-refresh.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 | $0.00157 | $0.01021 |
| Opus 5 | $0.00078 | $0.00511 |
| Sonnet 5 | $0.00031 | $0.00204 |
| Haiku 4.5 | $0.00016 | $0.00102 |
Grade A, and why
plugin-refresh 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 2d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin-refresh — refresh the plugin, and prove it by content
node scripts/plugin-refresh.mjs is the whole procedure. This file is not a copy of it.
node scripts/plugin-refresh.mjs --check # is it stale? changes nothing
node scripts/plugin-refresh.mjs # refresh, then prove it
node scripts/plugin-refresh.mjs --dry-run # print the plan, write nothing
--check also runs at SessionStart, as one line under the proof schedule. If that line says
current, there is nothing to do here.
Why a program and not a checklist
Every step of this has a failure mode that reports success. Measured on this machine over two days, all four at once:
/reload-pluginsre-reads disk. It never refetches from GitHub, and will happily rebuild a cache directory out of a clone 56 commits stale.- The cache is keyed by version. If a stale snapshot already declares the new number, the reinstall records the new sha and reuses the directory holding the old bytes.
installed_plugins.jsonholds one entry per scope. Updating the one you thought about leaves the other behind — and the one that serves is not necessarily the one you expect. A local entry was found pinned to a version whose sha no longer existed, rebased away.- The version number, the plugin count, and the reload's own "N skills" line are all blind to every one of the above.
So the program refuses to call a refresh done unless the installed tree is byte-identical to the source it claims to come from.
Reading what it prints
The scope lines are what is on disk. The leases block is what running sessions have
actually loaded — <cache>/<version>/.in_use/ is a directory of leases, one entry per Claude
process id, and ~/.claude/sessions/<pid>.json names each one.
loaded by running sessions (.in_use leases — the bytes a session HAS, not what disk says):
0.24.0 create-cmp-a0 (this repo)
0.25.0 create-cmp-a0 (this repo)
A session under both an old and a new generation has reloaded — the old lease is simply not released until it exits. A session under only an older generation has not reloaded yet, and the program says so by name. This is the one signal that still discriminates when two versions ship identical skills, because it does not care what the bytes are, only who loaded them.
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.
- 2d ago First seen · 81 lines · 157 tokens per session scan A 21809b4eab3f
plugin-refresh is a skill published in the GitHub repository kvdm-co-pilot/create-cmp (0 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 1,021 once invoked, about $0.0008 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 2026-09-10.
Other skills, from other repositories
debugging-instruments
Debug and profile a fintech iOS/macOS app with LLDB (breakpoints, po/p/expression, bt, frame variable, image lookup -address, watchpoints), the Xcode Memory Graph Debugger (retain cycles, MallocStackLogging backtraces), and Instruments templates (Time Profiler / CPU Profiler, Allocations, Leaks, Hangs, Animation…
swift-concurrency
Modern Swift Concurrency on iOS - async/await, structured concurrency, Task and Task.detached, actor and @MainActor isolation, Sendable and Swift 6 strict concurrency, AsyncSequence/AsyncStream, TaskGroup, async let, and bridging callbacks with withCheckedContinuation. Use when writing async iOS code, fixing data…
error-handling-result
Typed error handling in Kotlin/KMP shared code - kotlin.Result and runCatching, modeling outcomes with sealed result types (sealed interface with Success/Failure), and Arrow's Either, the either {} builder, and the Raise DSL (raise, bind, ensure, recover, context(Raise )). Use when designing how shared code reports…
kmp-logging
Multiplatform logging in Kotlin Multiplatform with Kermit (co.touchlab:kermit:2.0.7). Use when adding logging to shared code - the global Logger, severity levels (v/d/i/w/e/a), Logger.withTag for per-class tags, configuring LogWriters and minSeverity, building a custom Logger with StaticConfig, and routing…
perfetto-trace-analysis
Analyzes Perfetto traces to find the root cause of latency, memory, or jank issues in Android apps. Use when the user provides a Perfetto trace file and asks any question, ongoing investigation, or open-ended request to analyze its contents. Standalone quick path; for end-to-end profiling (recording a new trace + heap…
r8-analyzer
Analyzes Android build files and R8 keep rules to identify redundancies, broad package-wide rules, and rules that subsume library consumer keep rules. Use when developers want to optimize their app's size, remove redundant or overly broad keep rules, or troubleshoot Proguard configurations.