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 descriptive-skill-surface-admissiongit 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/descriptive-skill-surface-admission)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/descriptive-skill-surface-admission"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/descriptive-skill-surface-admission/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/descriptive-skill-surface-admission"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/descriptive-skill-surface-admission.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 | $0.00034 | $0.00507 |
| Opus 5 | $0.00017 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
descriptive-skill-surface-admission 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 10d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Descriptive Skill Surface Admission
Domain: tool-design Trigger: Use when a command or skill catalog mixes trusted local sources with external providers and you need a predictable rule for which entries may appear without manual curation. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Split listing admission into two lanes based on source trust. Automatically admit curated local sources such as bundled skills, project-local skills, or other maintained first-party directories because those entries can safely fall back to derived summaries when metadata is sparse. Require external or extensible sources such as plugins and MCP-provided entries to supply explicit human-readable description or trigger metadata before they appear in the user-facing surface. This keeps local discovery easy without letting opaque third-party items pollute the shared catalog.
Key Rules
- Decide admission from both source and metadata quality; provenance alone is not enough for external ecosystems.
- Maintain an allowlist for trusted local sources that may rely on derived descriptions instead of explicit descriptive fields.
- Require plugin, marketplace, or MCP-provided entries to expose meaningful descriptive metadata before listing them.
- Apply the admission filter only after excluding non-skill entries such as built-ins, disabled model-invocation commands, or non-prompt command types.
- Keep the rule deterministic and source-specific so users can predict why one class of skills auto-surfaces while another stays hidden until documented.
Example Application
If you are building a terminal assistant that loads skills from a local skills folder, a bundled starter pack, and several third-party MCP servers, let the bundled and project-local skills appear immediately even when they only have a first-line summary. For the MCP and plugin sources, hide entries until they declare a proper description or a clear when to use sentence, so the skill picker stays understandable instead of filling with opaque names.
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.
- 10d ago First seen · 29 lines · 34 tokens per session scan A 98b36b6f7d25
descriptive-skill-surface-admission is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 507 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
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.
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.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.