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 ariaxhan/kernel-claude --skill tearitapartgit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWrote 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/ariaxhan/kernel-claude/tearitapart)<a href="https://agentmods.dev/skills/ariaxhan/kernel-claude/tearitapart"><img src="https://agentmods.dev/badge/skills/ariaxhan/kernel-claude/tearitapart.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Agent Snooping · line 21 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 45 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 87 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00043 | $0.00920 |
| Opus 5 | $0.00022 | $0.00460 |
| Sonnet 5 | $0.00009 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
tearitapart 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 8d 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
<skill_load> Load: skills/quality/SKILL.md, skills/build/reference/testing.md, skills/tearitapart/reference/security.md Reference: skills/quality/reference/quality-research.md </skill_load>
<on_start>
agentdb read-start
</on_start>
output: scope: N files tier: 1|2|3 prior_work: contracts, research found
- input_validation: Zod schema? Parameterized queries?
- edge_cases: null, empty, unicode, timeout?
- error_handling: no empty catch? Logged with context?
- duplication: same logic repeated?
- complexity: functions < 30 lines?
Use quick_checks from quality skill for detection.
critical:
- No hardcoded secrets
- Auth tokens in httpOnly cookies
- Rate limiting
- HTTPS enforced
injection:
- SQL: parameterized only
- XSS: DOMPurify
- CSRF: tokens on state changes
verify:
- Tests exist BEFORE implementation?
- Edge cases covered?
- Assertions specific (not toBeTruthy)?
- Mocks at boundaries only?
red_flags:
- "Will add tests later"
- 100% coverage, weak assertions
- No error path testing
verify:
- Follows existing patterns?
- Interface stability?
- Modular boundaries?
- Dependency direction correct?
<ask_user> Use AskUserQuestion when: verdict is REVISE or RETHINK Ask: "Verdict: {REVISE|RETHINK}. Want details on specific findings, or proceed with fixes?" Options: show details, proceed with fixes, override and proceed anyway </ask_user>
<output_format>
Save to _meta/reviews/{feature}-teardown.md:
# Tear Down: {feature}
reviewed: {timestamp}
tier: {1|2|3}
scope: {N files}
## Big 5
input_validation: pass|fail
edge_cases: pass|fail
error_handling: pass|fail
duplication: pass|fail
complexity: pass|fail
## Verdict: PROCEED | REVISE | RETHINK
{reasoning}
## Action Items
1. {fix with file:line}
</output_format>
<on_complete>
agentdb write-end '{"command":"tearitapart","verdict":"X","big5_violations":N}'
</on_complete>
What ships with it
2 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.
- 8d ago First seen · 150 lines · 43 tokens per session scan A 80cb799ac2b1
tearitapart is a skill published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 920 once invoked, about $0.0002 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
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
differential-review
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.
huggingface-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.