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 JustinGastby/Hermes-Mind-Skill --skill curate-skillsgit clone --depth 1 https://github.com/JustinGastby/Hermes-Mind-SkillWrote 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/justingastby/hermes-mind-skill/curate-skills)<a href="https://agentmods.dev/skills/justingastby/hermes-mind-skill/curate-skills"><img src="https://agentmods.dev/badge/skills/justingastby/hermes-mind-skill/curate-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/justingastby/hermes-mind-skill/curate-skills"><img src="https://agentmods.dev/badge/skills/justingastby/hermes-mind-skill/curate-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 | $0.00079 | $0.01048 |
| Opus 5 | $0.00039 | $0.00524 |
| Sonnet 5 | $0.00016 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
curate-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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curate Skills
A much lighter version of Hermes Agent's Curator: it keeps .claude/skills/
from accumulating stale or near-duplicate entries, but — unlike Hermes's
fully-automatic background Curator — it never touches a file without the
user confirming first. A wrong or premature archive/merge is worse than a
slightly untidy skills folder.
Two things this does, and neither one deletes anything
- Archive long-unused skills — move the skill's directory into
.claude/skills/.archive/. Recoverable, never destructive. - Merge near-duplicate skills into one broader skill, then archive the originals (not delete) so nothing is lost if the merge was wrong.
When to run this
- The Stop hook's curator sweep (
nudge-skill-distillation.js) nudged you with a list of skills that haven't been read in ~30 days. - The user explicitly asks to clean up, compress, or prune skills.
- While drafting a new skill in
distill-skill, you notice 2+ existing skills already cover very similar ground.
Workflow
- Survey the current skills. List
.claude/skills/*/SKILL.md(skip.archive/). For each, read the frontmattername+description, and check.claude/hooks/.state/skill-usage.jsonforuse_count/last_used_atif present. - Never touch these:
distill-skill,curate-skills— this project's own bundled skills.- Any skill whose
SKILL.mdfrontmatter containspinned: true. - Bundled/hub-installed skills the user didn't create locally, if that's distinguishable (e.g. skills that shipped with another tool/plugin).
- Draft a short proposal, not a file edit. Two independent lists:
- Archive candidates: name + how long unused (from the nudge message
or
skill-usage.json). - Merge candidates: which 2+ skills overlap, a proposed merged name + one-sentence description, and which old skills would be absorbed.
- Archive candidates: name + how long unused (from the nudge message
or
- Ask the user to confirm each list separately (a skill might be a merge candidate but not stale, or vice versa) — e.g. "这些技能好久没用了， 要不要归档？" / "这几个技能内容挺重叠的，要不要合并成一个？" Do not modify any file before the user agrees.
- On confirmed archive:
mkdir -p .claude/skills/.archivethen move the skill's whole directory there (keepreferences/,templates/,scripts/subfiles together — archive the full package, don't cherry-pick files). - On confirmed merge:
- Create
.claude/skills/<new-name>/SKILL.mdwith the combined procedure — write it fresh, don't just concatenate the old bodies. Fold overlapping steps together; keep pitfalls from all sources. - Move any
references//templates//scripts/subfiles the merged skill still needs into the new skill's directory. - Archive (not delete) each absorbed skill's original directory into
.claude/skills/.archive/so the merge is reversible.
- Create
- On no or no response, drop it — don't archive/merge and don't ask again this session.
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.
- 11d ago First seen · 96 lines · 79 tokens per session scan A a009f9bc6557
curate-skills is a skill published in the GitHub repository JustinGastby/Hermes-Mind-Skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,048 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 2026-08-31.
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…