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 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/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/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="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 | $0.00019 | $0.00547 |
| Opus 5.5 | $0.00008 | $0.00219 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 19 tokens to every session and 547 once invoked, about $0.0001 per session on Opus 5.5. 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.
too-deep-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| too-deep-skilllorem-dev/skillkeeper-test-repo | Skill | 2 | 2mo ago | MIT | A | 19 | Claude Code, Codex |
| pcbwayaklofas/kicad-happy | Skill | 1.6k | today | MIT | A | 119 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| happiness-skillkangarooking/cangjie-skill | Skill | 12k | 1mo ago | MIT | A | 136 | Claude Code, Codex |
| remotion-best-practicesguanyang/open-agent-hub | Skill | 986 | today | MIT | A | 116 | Claude Code |
| influence-psychologywondelai/skills | Skill | 2.6k | 5d ago | MIT | A | 156 | Claude Code |
| jobs-to-be-donewondelai/skills | Skill | 2.6k | 5d ago | MIT | A | 137 | Claude Code |