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 hyh0620/mcp-knowledge-service --skill package-cleangit clone --depth 1 https://github.com/hyh0620/mcp-knowledge-serviceWrote 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/hyh0620/mcp-knowledge-service/package-clean)<a href="https://agentmods.dev/skills/hyh0620/mcp-knowledge-service/package-clean"><img src="https://agentmods.dev/badge/skills/hyh0620/mcp-knowledge-service/package-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/hyh0620/mcp-knowledge-service/package-clean"><img src="https://agentmods.dev/badge/skills/hyh0620/mcp-knowledge-service/package-clean.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 | $0.00022 | $0.00263 |
| Opus 5.5 | $0.00009 | $0.00105 |
| Sonnet 5.5 | $0.00004 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
package-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 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.
What it actually says
Package Clean
Pipeline
- Dry-run file scan:
find . -maxdepth 3 -type d \( -name .venv -o -name data -o -name logs -o -name __pycache__ -o -name .pytest_cache \) - Confirm
.gitignoreexcludes:.envconfig/settings.yaml.venv/data/logs/- caches
- Search for old or sensitive content:
git grep -n -I -E "(api[_-]?key|secret|token)[[:space:]]*[:=][[:space:]]*[^< ]{12,}|old-project-name|legacy-author" - Remove runtime directories only after confirming they are generated artifacts.
- Keep public examples under
examples/.
Output
- Files excluded.
- Findings that require manual review.
- Final clean status.
Rules
- Do not delete source documents in
examples/salon. - Do not print or copy secrets.
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 · 38 lines · 22 tokens per session scan A bf0b2d060dcd
package-clean is a skill published in the GitHub repository hyh0620/mcp-knowledge-service (0 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 263 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 2026-09-01.
Other skills, from other repositories
release-process
Skill "release-process" from Azure-Samples/eShopLite, covering release process, scope, confidence: high, context and rules (non-negotiable).
ralph-two-pass-scan
Confidence: high Domain: work-monitoring Last validated: 2026-03-24.
moraine-author-pr
Create Moraine pull requests on GitHub. Use when the branch is ready to open a PR; when the user asks to create, push, or open a PR; after local changes are committed; or when documenting user-facing features, bug fixes, performance optimizations, validation, changelog impact, or operational impact in a PR that…
moraine-start-work
Start Moraine repository development work safely. Use when an agent takes on new code, docs, test, CI, packaging, or release work in this repo; when it must create or verify an isolated branch/worktree; when sibling agent collisions are possible; or before editing files for a Moraine contributor task.
zen-comprehensive-review
Orchestrate a multi-model code review: spawn 3 review subagents, merge findings. In PR mode, posts GitHub PR comments with reactions. In local mode, outputs findings directly. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.
git-workflow
Automate the complete Git development workflow — create feature branches with conventional naming, atomic commits with conventional commit messages, interactive rebase, squash merges, PR body generation from commit history, branch cleanup, and git worktree patterns. Use when user asks to create a branch, commit…