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/too-deep-skillnpx skills add lorem-dev/skillkeeper-test-repo --skill too-deep-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/too-deep-skill)<a href="https://agentmods.dev/skills/lorem-dev/skillkeeper-test-repo/too-deep-skill"><img src="https://agentmods.dev/badge/skills/lorem-dev/skillkeeper-test-repo/too-deep-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 | $0.00019 | $0.00547 |
| Opus 5 | $0.00010 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
too-deep-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 5d 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.
too-deep-skill
This skill is expected to fail resolution. It is a negative fixture.
It sits five path segments below the repository root
(deep-nesting/l2/l3/l4/too-deep-skill/SKILL.md) - four group levels plus the
skill directory. Auto-detection scans at most four levels: depth 1 for
ungrouped skills, depths 2 through 4 for grouped ones, so a group path
carries at most three segments. Anything deeper is reported rather than
guessed at.
Expected behaviour
The core resolver returns one warning naming this path, along the lines of:
Unresolved SKILL.md at "deep-nesting/l2/l3/l4/too-deep-skill": nesting is
deeper than 3 group levels; declare it in skillkeeper.repo.yaml to install it.
The important half is what does not happen: SkillKeeper does not silently
invent a group (deep-nesting, deep-nesting/l2, deep-nesting/l2/l3, or
deep-nesting/l2/l3/l4) and install the skill anyway. A warning plus no
install is the correct outcome.
The other twenty-four resolvable skills in this repository must still resolve normally. One unresolvable path never fails the rest of the listing.
The warning reaches standard error, prefixed with the repository name, on any
command that resolves skills - including a successful install of a different
skill. Installing this one by name prints the warning and then
Skill not found in any tracked repository: too-deep-skill, exiting 1.
The escape hatch
An explicit path in skillkeeper.repo.yaml reaches any depth. See
skillkeeper.repo.yaml.example at the repository root, which declares exactly
this path and renames it to rescued/rescued-skill. Rename that file to
skillkeeper.repo.yaml and this skill becomes installable - at the cost of
switching the whole repository to config-authoritative mode, where
auto-detection is skipped and only declared paths resolve.
If this fixture is in the way
deep-nesting/ is one of the two unresolvable paths in this repository; the
other is requires/invalid-strict, which fails for an unrelated reason. Delete
this directory and every other SKILL.md except that one resolves.
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.
- 5d ago First seen · 55 lines · 19 tokens per session scan A d8a083de8101
too-deep-skill is a skill published in the GitHub repository lorem-dev/skillkeeper-test-repo (2 stars, last pushed 11d ago), licensed MIT. It adds 19 tokens to every session and 547 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.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
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…