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 iusztinpaul/squid --skill squid-clean-harnessgit clone --depth 1 https://github.com/iusztinpaul/squidWrote 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/iusztinpaul/squid/squid-clean-harness)<a href="https://agentmods.dev/skills/iusztinpaul/squid/squid-clean-harness"><img src="https://agentmods.dev/badge/skills/iusztinpaul/squid/squid-clean-harness/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/iusztinpaul/squid/squid-clean-harness"><img src="https://agentmods.dev/badge/skills/iusztinpaul/squid/squid-clean-harness.svg" alt="Reviewed on agentmods" width="80" 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 107 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 109 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 110 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 | $0.00034 | $0.01755 |
| Opus 5 | $0.00017 | $0.00877 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
squid-clean-harness 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 4d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean harness — same logic, minimum tokens
You are the cleaner. You shrink the skills and resources a harness loads; you do not change what they make the agent do. Zero logic diff is the contract — every capability, step, and rule that holds before must hold after; only tokens die.
$ARGUMENTS is an optional .agents/ path (e.g. ~/Vaults/Second-Brain/.agents). Empty means the
repo's ./.agents.
When NOT to use — out of scope, no exceptions
| Excluded | Why |
|---|---|
resources/datasets/ |
Data the skills operate on, not logic. Never in scope. |
Memory files (AGENTS.md, CLAUDE.md) |
→ /squid-clean-memory. |
| Docs, READMEs, comments, docstrings | → /squid-clean-docs. |
| Skill names and argument shapes | The name is the API — a rename is an edit, not a cleanup. |
Step 1 — Resolve the target set
Inventory skills/*/SKILL.md and resources/** minus resources/datasets/ under the target
.agents/. Everything must be revertible: clean in git, or snapshot first
(cp -R .agents .agents.bak) when the tree isn't tracked.
Step 2 — Audit the contract (frontmatter)
Two questions per skill:
- Invocation type — auto-fired by the model, or only typed by the user? User-only →
disable-model-invocation: true, keeping its description out of the always-loaded skill list. Flipping also cuts reach from other skills — grep the set for the skill's name first (Step 4's proof); one referrer means it stays model-invoked. - Description — must match what the body does. Model-invoked → triggers only, one per branch: synonyms naming the same branch are duplication ("build with TDD" / "asks for test-first development" is one branch written twice). User-only → one sentence of what it does; trigger prose serves no router — delete it.
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.
- 4d ago Changed · -16 lines d95156bb1ca6
- 9d ago First seen · 155 lines · 34 tokens per session scan A 038910a19c0b
squid-clean-harness is a skill published in the GitHub repository iusztinpaul/squid (186 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,755 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
ai-assist-prototype
Build self-contained, double-click-to-open HTML prototypes so the user can vet an interface before it gets built. One file holds several structurally different variants of a page, app screen, component, flow, or terminal/TUI layout (rendered in-browser), plus a draggable Design Deck for flipping between variants…
ai-assist-git-pr-review
Perform a standards-based code review on a GitHub Pull Request, then post the findings as inline review comments and mark the PR as 'Requested changes'. Reads all of the agents files that exist in the repository under review (AGENTS.md, .agents-docs/, CLAUDE.md on the PR's base branch) — the repo's full documented…
ai-assist-git-pr
Adaptive GitHub PR lifecycle skill — create PRs, write/update descriptions, investigate review comments (Copilot + human) with research and batch approval, and check merge readiness. Triggers on: create PR, open PR, describe PR, update description, PR body, check comments, copilot feedback, review comments, address…
ai-assist-design-creator
Reverse-engineer a website's visual design system from a URL and produce a fully spec-compliant DESIGN.md file (https://github.com/google-labs-code/design.md). The output includes both machine-readable YAML design tokens (colors, typography, spacing, rounded corners, components) and human-readable markdown rationale…
ai-assist-dockerize-website
Guide the user through containerizing and serving a simple website or documentation folder with Docker — inspects the project to detect what to serve (ready-to-serve static HTML, a buildable site that emits static output, or a raw markdown/docs folder that needs rendering), generates a Dockerfile, .dockerignore…
ai-assist-changelog-bump
Validate and fix the CHANGELOG.md version number before opening a PR, commiting, or pushing changes, and keep package.json's version aligned with it. Reads main branch to determine the current latest version, classifies changes on the current branch, and proposes the correct next semver. Use this skill when the user…