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 flavien-ia/hypervibe-harness --skill cleangit clone --depth 1 https://github.com/flavien-ia/hypervibe-harnessWrote 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/flavien-ia/hypervibe-harness/clean)<a href="https://agentmods.dev/skills/flavien-ia/hypervibe-harness/clean"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/clean/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/flavien-ia/hypervibe-harness/clean"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/clean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
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 →
- high Privilege Escalation · line 47 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 435 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Privilege Escalation · line 81 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 143 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 144 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 145 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 306 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 50 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00075 | $0.07488 |
| Opus 5 | $0.00037 | $0.03744 |
| Sonnet 5 | $0.00015 | $0.01498 |
| Haiku 4.5 | $0.00007 | $0.00749 |
Grade A, and why
clean 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean - Project hygiene audit
Communication
- Detect the user's language from the conversation (the user's own messages, anywhere in the session - not just this invocation: a bare slash command like
/bootstrapcarries no language signal by itself). If nothing in the conversation gives a signal, fall back to the OS locale (node -e "console.log(Intl.DateTimeFormat().resolvedOptions().locale)") before defaulting to English. ALWAYS reply in that language for every user-facing message: questions, progress, confirmations, summaries, errors - including any example text quoted in this skill, which is illustrative and must be translated, never sent verbatim. - Use plain, non-technical business language. Never expose internal script names (*.mjs) or jargon; describe actions in human terms.
- When generating user-facing content for the scaffolded project (UI labels, emails, copy), write it in the user's language too.
- Show progress as a short natural-language checklist (in-progress and done states).
You audit the project to find what is no longer used, then you propose deletions on a separate branch so the user can verify before merging.
Disclaimer to display at the start of the audit:
⚠️ This report is a diagnostic. Some findings are false positives: your code may use elements in a way that static analysis cannot detect (dynamic imports, references in the database, an env var read by a transitive dependency, external links to pages, and so on). Nothing will be deleted without your explicit approval, and the deletions will be made on a separate branch that you test before merging.
Educational rule (important)
The report must be readable by someone who is not a developer. You may be dealing with a user who knows what they want, but not all the technical jargon.
Concrete rules:
- When you use a technical term, explain it immediately in parentheses the first time it appears. Example: "An unused export (a function or component exposed by a file, but that no other file picks up)".
- When you can, prefer a common rephrasing and put the technical term in parentheses. Example: "This file contains bits of code that are saved but never called (dead code)".
- Use everyday analogies for abstract concepts: a
.bakfile = "a forgotten photocopy", an unused dependency = "a tool in the toolbox that no one uses", a DB table with no caller = "a storage room that no one has the key to". - For the checks the user has to do, explain what verifying it is for - not just the action to take. Example of a bad phrasing: "Check
grep -r 'Foo'". Example of a good phrasing: "Open a terminal and typegrep -r 'Foo' src/- you should only see the file that defines Foo. If you see other files, that means Foo is used somewhere, and you must not delete it." - Never be condescending. The user is intelligent, they just do not know this domain.
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.
- 5d ago First seen · 450 lines · 75 tokens per session scan A 1b644a087d8c
clean is a skill published in the GitHub repository flavien-ia/hypervibe-harness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 7,488 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 2026-09-04.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
gsd-audit-fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.
git-worktree-precommit-hook-flutter-failure
Fix git pre-commit hook failures in Flutter projects when using git worktrees. Use when: (1) Pre-commit hook with flutter analyze fails during git commit but passes when run manually, (2) Hook output shows "Resolving dependencies..." then immediately fails with no actual analysis errors, (3) Working in a git worktree…
git-mastery
Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.
magpie-setup-upstream-fix
Turn a framework bug or quirk the agent hit while running a Magpie skill or tool into a fix PR against apache/magpie — one PR per issue. First confirms the problem is a framework defect (not a local misconfiguration or a stale snapshot), then searches apache/magpie for an existing issue or PR that already covers it…
stage-payload-reverts
Create TRT JIRA bugs, open revert PRs, and trigger payload jobs for high-confidence revert candidates.