Borrowing it
Nothing to install: this file belongs to victoriacity/openakari. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/victoriacity/openakari/main/.claude/skills/refresh-skills/SKILL.mdgit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/refresh-skills)<a href="https://agentmods.dev/skills/victoriacity/openakari/refresh-skills"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/refresh-skills/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/victoriacity/openakari/refresh-skills"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/refresh-skills.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 | $0.01868 |
| Opus 5 | $0.00015 | $0.00934 |
| Sonnet 5 | $0.00006 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
refresh-skills 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 9d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refresh-skills
Skills encode operational guidance, but the codebase evolves faster than skills get updated. This skill audits skills against the current source code, identifies drift, and applies fixes.
The argument determines scope:
| Argument | Behavior |
|---|---|
all |
Audit every skill, update all that need it |
report |
Audit every skill, report drift but don't edit |
<skill-name> |
Audit and update one specific skill |
| (no argument) | Same as all |
Step 1: Inventory
Read every SKILL.md under .claude/skills/*/. For each, extract:
- Name and description
- Source references — which infra files, functions, types, or patterns does this skill reference? (Look for file paths, function names, type names, action tags, command examples, tool lists)
- Status — is it marked
draft?
Step 2: Cross-reference against source
For each skill's source references, read the actual current code. Check for:
Description compliance (CSO convention)
Skill descriptions are injected into Claude's system prompt for skill selection. They must state ONLY triggering conditions — never summarize the skill's workflow or process.
Rule: Descriptions answer "When should I invoke this?" not "What does this skill do?"
Why: Testing (cross-project skill-pollination experiment, Finding 1) showed that descriptions summarizing workflow cause Claude to shortcut — following the description instead of reading the full skill body. A description saying "code review between tasks" caused Claude to do ONE review when the skill required TWO.
Checklist for each description:
- Does it describe a situation, symptom, or trigger? (good)
- Does it summarize the skill's process or output? (bad — rewrite)
- Does it use verbs that describe the skill's actions (e.g., "analyze", "generate", "validate")? (bad — replace with triggering conditions)
Format:
# ❌ BAD: Summarizes workflow
description: "Process human feedback — investigate root cause, log learnings, and implement improvements"
# ✅ GOOD: Triggering condition only
description: "Use when the PI or a human provides feedback, corrections, or direction on agent work"
# ❌ BAD: Describes what the skill does
description: "Generate reports — operational dashboard, research digest, project status"
# ✅ GOOD: Triggering condition
description: "Use when a status report, digest, or dashboard is needed for human review"
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.
- 9d ago First seen · 167 lines · 30 tokens per session scan A 0c1003d9364c
refresh-skills is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 1,868 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…