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 skill-registry-composition-and-feature-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/skill-registry-composition-and-feature-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/skill-registry-composition-and-feature-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-registry-composition-and-feature-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/skill-registry-composition-and-feature-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-registry-composition-and-feature-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 | $0.00032 | $0.00458 |
| Opus 5 | $0.00016 | $0.00229 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
skill-registry-composition-and-feature-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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Skill Registry Composition and Feature Gating
Domain: command-surfaces
Trigger: Use when a coding agent assembles skills or prompt commands from multiple sources and optional features can enable, disable, or delay some of them.
Source Pattern: Distilled from reviewed command-surface, registry-bootstrap, and dynamic-skill loading implementations.
Core Method
Assemble the registry in explicit phases instead of letting sources merge opportunistically. Start from the always-on local surface, then layer bundled skills, project-local skills, plugin-provided entries, and remote or MCP-discovered skills in a stable order. Apply feature gates before importing or materializing each optional phase so disabled sources do not cost startup time or leak partial entries into the merged view. After composition, dedupe by canonical command identity and memoize the final snapshot so listing, search, and execution all see the same result.
Key Rules
- Keep the phase order fixed and documented so later additions do not silently change precedence.
- Check feature gates before loading optional modules or scanning optional sources.
- Deduplicate after all enabled sources are collected, using one canonical identity rule for listing and execution.
- Cache the merged snapshot, not just individual source scans, so downstream consumers stay in sync.
- Invalidate every derived surface that depends on the merged registry when any source changes.
Example Application
If a terminal coding agent loads built-in skills, project-local skills, and MCP-discovered prompt tools, first collect the always-on built-ins, then project-local skills, then gated remote sources. Dedupe the combined list, cache that snapshot, and feed the same snapshot to help menus, slash-command discovery, and command execution.
Anti-Patterns (What NOT to do)
- Don’t let optional sources self-register at import time before checking whether the feature is enabled.
- Don’t dedupe each source independently and assume the final merged list will stay clean.
- Don’t let help text, search, and execution build separate registry snapshots from different source orders.
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 · 30 lines · 32 tokens per session scan A 3194081d53a2
skill-registry-composition-and-feature-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 458 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 2026-09-03.
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.