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 built-in-agent-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/built-in-agent-feature-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/built-in-agent-feature-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/built-in-agent-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/built-in-agent-feature-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/built-in-agent-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 | $0.00025 | $0.00388 |
| Opus 5 | $0.00013 | $0.00194 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
built-in-agent-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 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.
What it actually says
SKILL: Built-In Agent Feature Gating
Domain: agent-management Trigger: Use whenever agent registration should respect CLI entrypoints, SDK toggles, or feature flags before exposing the built-in catalog. Source Pattern: Distilled from reviewed built-in agent registration and feature-flagged runtime catalog implementations.
Core Method
Check entrypoint type, environment toggles, and feature flags before adding each built-in agent to the visible registry. Different entrypoints often need different built-in surfaces: a CLI may want planning or guidance agents, while an SDK or embedded runtime may want a minimal default set. Treat special orchestration modes as their own catalog variant rather than layering them on top of the normal list. This keeps built-in agents discoverable where they belong without leaking extra helpers into every runtime surface.
Key Rules
- Support an explicit “disable built-ins” toggle for SDK or embedded contexts that should expose a minimal surface.
- Treat coordination or orchestration modes as a separate built-in catalog rather than mixing them into the default list.
- Gate specialized built-ins behind feature flags or experiments instead of making them permanently visible.
- Keep the gating logic centralized so every entrypoint evaluates the same rules consistently.
Example Application
Before populating the agent registry, apply these checks so an SDK session can expose no built-ins, a CLI can expose planning or guidance agents when enabled, and a coordinator runtime can swap in its own worker-oriented catalog.
Anti-Patterns (What NOT to do)
- Don’t register all built-in agents unconditionally; ignoring entrypoints or env vars breaks SDK/CLI separation.
- Avoid hardcoding agent lists per mode; fold them into feature flags and helper functions to stay configurable.
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 · 25 tokens per session scan A 1bc5a3e2ca6b
built-in-agent-feature-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 388 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 2026-08-30.
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.