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 agentmods add skills/l3digitalnet/claude-code-plugins/refresh-plugin-cachenpx skills add L3DigitalNet/Claude-Code-Plugins --skill refresh-plugin-cachegit clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-PluginsWhat 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 | $0.00096 | $0.01503 |
| Opus 5 | $0.00048 | $0.00751 |
| Sonnet 5 | $0.00019 | $0.00301 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade C, and why
refresh-plugin-cache scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Orphaned directories**: list sizes, offer to delete with `rm -rf`. How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Plugin Cache
Pull the latest l3digitalnet-plugins marketplace index, compare installed plugin versions against current listings, and surface anything stale or orphaned. The claude-plugins-official marketplace is managed by Anthropic and excluded from this workflow.
Workflow
Step 1 — Run the refresh script
bash .claude/skills/refresh-plugin-cache/scripts/refresh-cache.sh
Run from the project root (/home/chris/projects/Claude-Code-Plugins). The script does not modify installed plugin content — it only updates the marketplace index clones and reports status.
Step 2 — Interpret the output
MARKETPLACE INDEX REFRESH — One line per marketplace git clone:
| Prefix | Meaning |
|---|---|
OK |
Already at latest main; SHA shown for confirmation |
UPDATE |
Pulled new commits; before → after SHAs shown |
ERROR |
git fetch failed — likely offline; cached data still usable |
SKIP |
Directory exists but is not a git repo |
INSTALLED PLUGIN VERSION CHECK — Compares installed version (from installed_plugins.json) against the freshly-pulled marketplace listing, for l3digitalnet-plugins only. Does not reflect what is actually running — see LIVE MCP PROCESS CHECK below.
| Label | Meaning |
|---|---|
STALE |
Installed version differs from marketplace; reinstall needed |
CURRENT |
Installed version matches marketplace |
LIVE MCP PROCESS CHECK — Compares the version embedded in the path of each running Node.js MCP process against the version in installed_plugins.json:
| Label | Meaning |
|---|---|
LIVE_OK |
Running process path version matches installed version |
LIVE_SKEW |
Running process started from an older path; installed_plugins.json was updated mid-session but Claude Code didn't restart the process. Normal reinstall won't fix this — use the hot-patch procedure below. |
NOT_RUNNING |
Plugin is installed but no live process found (MCP not started, or non-MCP plugin) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 112 lines · 96 tokens per session scan C f4cef0cc583d
refresh-plugin-cache is a skill published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,503 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…