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 jon-devlapaz/tink-skills --skill skill-gategit clone --depth 1 https://github.com/jon-devlapaz/tink-skillsWrote 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/jon-devlapaz/tink-skills/skill-gate)<a href="https://agentmods.dev/skills/jon-devlapaz/tink-skills/skill-gate"><img src="https://agentmods.dev/badge/skills/jon-devlapaz/tink-skills/skill-gate/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/jon-devlapaz/tink-skills/skill-gate"><img src="https://agentmods.dev/badge/skills/jon-devlapaz/tink-skills/skill-gate.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 | $0.00048 | $0.01716 |
| Opus 5.5 | $0.00019 | $0.00686 |
| Sonnet 5.5 | $0.00010 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade B, and why
skill-gate scanned grade B with 3 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 1mo 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `destructive_ops` | 0.35 | `shutil.rmtree`, `os.system` removals, `rm -rf`, `truncate`, `dd if=` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `external_network` | 0.25 | `urllib`, `requests`, `socket`, `curl`, `wget`, `nc` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `destructive_ops` | 0.35 | `shutil.rmtree`, `os.system` removals, `rm -rf`, `truncate`, `dd if=` | How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Gate
Skill Gate provides standard-library-only static feature extraction, multi-factor risk profiling, and harness compatibility evaluation for AI agent skills.
Invariant: Skill Gate is strictly static and read-only. It never executes
untrusted skill code, executes shell scripts, or makes network calls. It inspects
SKILL.md, AST nodes from Python scripts, and lexical tokens from shell scripts to
derive deterministic vectors and evaluate risk boundaries.
Audit Workflow
When evaluating a candidate skill (e.g. under skills/<name> or an untrusted external directory):
- Run Static Audit:
Execute
skill_gate.pyagainst the target skill directory from the repo root:python3 skills/skill-gate/skill_gate.py <skill_dir> --json --check-compat pi - Evaluate the Risk Verdict:
- ALLOW (
score < 0.30, no redlines): Safe for adoption; conforms to static boundaries. - WARN (
0.30 <= score < 0.70, no redlines): Contains network imports or sensitive environment variable lookups. Review findings before adopting. - BLOCK (
score >= 0.70or redline triggered): Contains critical threats (dynamic code evaluation, root filesystem operations, raw secret exfiltration). Do not adopt or execute without remediation.
- ALLOW (
- Verify Harness Compatibility:
Confirm whether declared tools match the target harness (
pi,claude,codex,generic). Ifincompatible, review missing tools before continuing.
Architecture
The engine runs as a multi-stage static analysis pipeline:
Skill Directory (SKILL.md, *.py, *.sh)
│
├── 1. parse_frontmatter() ── YAML frontmatter (name, tools, metadata)
├── 2. analyze_python_code() ── AST imports, dangerous calls, env lookups, writes
└── 3. scan_shell_script() ── Lexical tokens (destructive, network, creds, autonomy)
│
▼
extract_features()
├── Asset metrics (file counts, total bytes)
├── 8D continuous normalized vector [0.0 - 1.0]
└── Canonical sha256:<hex> vector hash
│
┌───────────────┴───────────────┐
▼ ▼
profile_risk() evaluate_compatibility()
- destructive_ops (0.35) - Target harness: pi, claude, codex, generic
- external_network (0.25) - Tool presence check
- credential_exposure (0.25) - Missing tool detection
- autonomy_escalation (0.15) - Compatibility verdict
- Critical redline triggers
- ALLOW / WARN / BLOCK
│ │
└───────────────┬───────────────┘
▼
analyze_skill()
Unified SkillAuditReport
What ships with it
9 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.
- 1mo ago Changed aa2b4721ce99
- 1mo ago First seen · 162 lines · 48 tokens per session scan B f24b61b04bec
skill-gate is a skill published in the GitHub repository jon-devlapaz/tink-skills (16 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 1,716 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 3 findings (recursive force delete, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.