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 ychampion/cskill-agents --skill trusted-frontmatter-gatinggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/trusted-frontmatter-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/trusted-frontmatter-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/trusted-frontmatter-gating/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/ychampion/cskill-agents/trusted-frontmatter-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/trusted-frontmatter-gating.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 | $0.00029 | $0.00426 |
| Opus 5 | $0.00015 | $0.00213 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
trusted-frontmatter-gating 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Trusted Frontmatter Gating
Domain: frontmatter-gating Trigger: Apply this pattern when you are about to honor MCP servers, hooks, or skill preloads declared in an agent’s frontmatter while the session may be locked to plugin-only/customized trust settings. Source Pattern: Distilled from reviewed subagent orchestration, isolation, and lifecycle implementations.
Core Method
Before activating any frontmatter-declared resources, run them through the runtime trust policy. Approved sources may attach extra MCP servers, lifecycle hooks, or preloaded skills; untrusted sources should be skipped with a clear warning instead of being half-initialized. Evaluate each resource class independently so a session can allow one category while restricting another. When preloading skills, resolve each declared name against the known catalog first and only inject entries that map to an allowed skill surface.
Key Rules
- Evaluate MCP servers, hooks, and skill preloads separately so policy can restrict one class without blocking the others.
- Decide trust before activation; never connect extra servers or register hooks for unapproved frontmatter sources.
- Scope approved hooks and integrations to the child agent lifecycle so teardown remains local and deterministic.
- Resolve declared skill names against the known catalog before injection, and warn when a requested skill is missing or disallowed.
Example Application
If a user-authored agent asks to preload extra servers, hooks, and skills while the runtime is locked to approved extensions only, this pattern lets trusted packaged agents proceed while user-controlled frontmatter is rejected with clear diagnostics instead of silently widening the trust boundary.
Anti-Patterns (What NOT to do)
- Don’t treat every frontmatter resource as equally trusted; skipping the trust check lets user-authored definitions bypass extension policy.
- Don’t preload skills by raw name without catalog resolution; unresolved or remapped names will fail later in harder-to-debug ways.
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 · 28 lines · 29 tokens per session scan A b46a72027946
trusted-frontmatter-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 426 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.