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 pengguanya/claude-toolkit --skill publish-skillgit clone --depth 1 https://github.com/pengguanya/claude-toolkitWrote 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/pengguanya/claude-toolkit/publish-skill)<a href="https://agentmods.dev/skills/pengguanya/claude-toolkit/publish-skill"><img src="https://agentmods.dev/badge/skills/pengguanya/claude-toolkit/publish-skill/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/pengguanya/claude-toolkit/publish-skill"><img src="https://agentmods.dev/badge/skills/pengguanya/claude-toolkit/publish-skill.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 | $0.00017 | $0.02673 |
| Opus 5 | $0.00009 | $0.01337 |
| Sonnet 5 | $0.00003 | $0.00535 |
| Haiku 4.5 | $0.00002 | $0.00267 |
Grade C, and why
publish-skill 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 10d 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.
rm -rf $SKILLS_DIR/<name> How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Skill
Manage skills between a private skills directory and a public toolkit repo.
Configuration
This skill stores its configuration in a JSON file next to this SKILL.md:
<skill-base-dir>/config.json
The config file contains:
{
"SKILLS_DIR": "~/.claude/skills",
"TOOLKIT_DIR": "~/path/to/your/toolkit",
"TOOLKIT_SKILLS": "~/path/to/your/toolkit/skills"
}
First-run setup
Before executing ANY workflow, check if config.json exists in this skill's directory. If it does NOT exist:
- Tell the user: "This is your first time running publish-skill. I need to know where your toolkit repo and skills directory are."
- Ask for SKILLS_DIR — "Where are your Claude Code skills stored?" (default:
~/.claude/skills) - Ask for TOOLKIT_DIR — "Where is your public toolkit git repo?" (no default — user must provide this)
- Set TOOLKIT_SKILLS to
$TOOLKIT_DIR/skillsand confirm with user - Write the config to
config.jsonnext to this SKILL.md - Continue with the requested workflow
If config.json exists, read it and use those values for all paths below.
All commands below use $SKILLS_DIR, $TOOLKIT_DIR, and $TOOLKIT_SKILLS — substitute the values from config.json.
Arguments
$ARGUMENTS
| Input | Action |
|---|---|
promote <skill-name> |
Move private skill to public toolkit, replace local with symlink |
fork <skill-name> [--public-name <name>] |
Create generalized public copy, keep private version |
adopt <skill-name-or-url> |
Install public skill and customize as private |
status |
Show which skills are private, public, or symlinked |
diff <skill-name> |
For forked skills: show diff between private and public versions |
Empty or help |
Explain available modes |
Workflow: Status
Run this first to understand the current state.
# List all skills and their status
for dir in $SKILLS_DIR/*/; do
name=$(basename "$dir")
if [ -L "${dir%/}" ]; then
target=$(readlink -f "${dir%/}")
echo "SYMLINKED $name -> $target"
elif [ -d $TOOLKIT_SKILLS/"$name" ]; then
echo "FORKED $name (private + public versions)"
else
echo "PRIVATE $name"
fi
done
# Show public skills not installed locally
for dir in $TOOLKIT_SKILLS/*/; do
name=$(basename "$dir")
[ -e $SKILLS_DIR/"$name" ] || echo "PUBLIC_ONLY $name (not installed locally)"
done
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.
- 10d ago First seen · 282 lines · 17 tokens per session scan C f3301adbafe0
publish-skill is a skill published in the GitHub repository pengguanya/claude-toolkit (2 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 2,673 once invoked, about $0.0001 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.
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…