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 pc-style/cool-my-skills --skill search-cold-skillsgit clone --depth 1 https://github.com/pc-style/cool-my-skillsWrote 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/pc-style/cool-my-skills/search-cold-skills)<a href="https://agentmods.dev/skills/pc-style/cool-my-skills/search-cold-skills"><img src="https://agentmods.dev/badge/skills/pc-style/cool-my-skills/search-cold-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/pc-style/cool-my-skills/search-cold-skills"><img src="https://agentmods.dev/badge/skills/pc-style/cool-my-skills/search-cold-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 10 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 11 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00075 | $0.00911 |
| Opus 5 | $0.00037 | $0.00456 |
| Sonnet 5 | $0.00015 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
search-cold-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
[!WARNING] cool-my-skills has been copied here, but it has not been installed.
This usually happens after a copy-only install such as
npx skills add. That copies this skill, but it does not create~/.agents/skills-cold/or finish initialization.Do not search cold skills yet. Tell the user it is not installed, then ask if they want to run this embedded initialization script:
bash "$(dirname "$0")/scripts/install.sh" # or, from this skill's dir: bash scripts/install.shOn Windows (PowerShell 7+), run it with:
pwsh "$HOME\.agents\skills\search-cold-skills\scripts\install.ps1" # or, from this skill's dir: pwsh .\scripts\install.ps1Before asking, explain that the script will only:
- create
~/.agents/skills-cold/- remove this warning from this copied
SKILL.md- make
scripts/query.shexecutable (unix only)After the user agrees and the script completes, ask whether they want to call any cold skills now. If they want the interactive picker for moving existing skills into cold storage, tell them to run the repo's
setup.shorsetup.ps1instead.
Search Cold Skills
Cold skills live at ~/.agents/skills-cold/<skill-name>/. They are intentionally outside your agent's auto-discovered skill directories to reduce always-loaded skill metadata (fewer trigger tripwires on every message).
Trigger phrases: cold <skill-name>, cold <query>, "search your skills", "search cold skills", "use a cold skill", "find a hidden skill".
When invoked:
-
Extract the query (everything after
cold/ the trigger phrase). It may be an exact skill name or a fuzzy description. -
Run the helper script.
On unix:
~/.agents/skills/search-cold-skills/scripts/query.sh <query>On Windows (PowerShell 7+):
pwsh "$HOME\.agents\skills\search-cold-skills\scripts\query.ps1" <query>It regenerates
skills-cold/INDEX.md, searches it (trying hyphenated, stemmed, and partial-word variants of the query), falls back to hot skills if nothing matches, and suggests--deep(full SKILL.md body search) as a last resort. -
If the script is unavailable, search manually under
~/.agents/skills-coldwithrg(unix) orSelect-String(PowerShell), preferring frontmattername:anddescription:matches, and try hyphenated/stemmed/partial variants of the query before giving up. -
If exactly one skill clearly matches, read that cold skill's
SKILL.mdfully. -
If several skills match, show the likely matches and ask the user to choose unless one is clearly strongest.
-
If no cold skill matches but a hot (auto-loaded) skill does, use the hot skill — but explicitly tell the user you fell back to a hot skill.
-
Treat the matched cold skill directory as the skill root. Resolve
scripts/,references/,resources/, and other relative paths under that cold skill directory. -
Follow the cold skill's instructions manually for this request.
-
Respect compatibility, environment, MCP, and tool notes in the cold skill frontmatter/body, but remember your agent will not automatically apply cold skill metadata.
What ships with it
4 files 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.
- 12d ago First seen · 72 lines · 75 tokens per session scan A dcc71fea39f3
search-cold-skills is a skill published in the GitHub repository pc-style/cool-my-skills (24 stars, last pushed 27d ago), licensed MIT. It adds 75 tokens to every session and 911 once invoked, about $0.0004 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…