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/lorem-dev/skillkeeper-test-repo/json-hooks-skillnpx skills add lorem-dev/skillkeeper-test-repo --skill json-hooks-skillgit clone --depth 1 https://github.com/lorem-dev/skillkeeper-test-repoWrote 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/lorem-dev/skillkeeper-test-repo/json-hooks-skill)<a href="https://agentmods.dev/skills/lorem-dev/skillkeeper-test-repo/json-hooks-skill"><img src="https://agentmods.dev/badge/skills/lorem-dev/skillkeeper-test-repo/json-hooks-skill.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00550 |
| Opus 5 | $0.00010 | $0.00275 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
json-hooks-skill 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
json-hooks-skill
Install this skill for claude, codex, copilot, or cursor - the four agents
whose hook strategy is json-merge. Its hook payloads are JSON objects.
Install it with hooks
Hooks are privileged and never installed implicitly:
skillkeeper skill install json-hooks-skill --agent claude --allow-hooks
Without --allow-hooks the body installs and both hooks are skipped with a
notice - which is itself worth testing.
What this fixture covers
- The named hook layout,
hooks/<hookName>/HOOK.md. Two hook directories prove more than one hook per skill resolves. (text-hook-skillcovers the other layout, a singlehooks/HOOK.md.) hooks/is reserved: nothing under it counts as a skill body file. After install this skill's body isSKILL.md,GUIDE.md, and.skid.yml- the hook files are not copied, they are merged into the agent's config.- Two different
keyPathvalues (hooks.PreToolUseandhooks.PostToolUse), so the merge has to create two separate arrays. - The
_skillkeeperownership marker. Each merged node carries one, with amarkerIdderived from the hook's label. Uninstall removes exactly the owned nodes and preserves any hook entry you added by hand to the same file - worth checking by putting your own entry inhooks.PreToolUsefirst. - Sorted key order in the rewritten JSON, so re-installing the same content is a no-op diff.
GUIDE.mdwith noRULES.md: the fourth guidance case.
Why the payloads are JSON
HOOK.md declares strategy and target.agent, but install consults
neither. The strategy comes from the adapter of whichever agent you are
installing for, and every hook in the skill is applied with that one strategy -
there is no filtering by target.agent. So a payload has to match the
installing agent, not what HOOK.md says.
Installing this skill for opencode therefore inserts these JSON objects as
raw text into a delimited region. Use text-hook-skill for opencode instead.
What ships with it
5 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.
- 4d ago First seen · 55 lines · 20 tokens per session scan A 39f79df12f31
json-hooks-skill is a skill published in the GitHub repository lorem-dev/skillkeeper-test-repo (2 stars, last pushed 11d ago), licensed MIT. It adds 20 tokens to every session and 550 once invoked, about $0.0001 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
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…
jobs-to-be-done
Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…