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 bundled-and-mcp-turn-zero-skill-filtergit 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/bundled-and-mcp-turn-zero-skill-filter)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter/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/bundled-and-mcp-turn-zero-skill-filter"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter.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 | $0.00040 | $0.00451 |
| Opus 5 | $0.00020 | $0.00226 |
| Sonnet 5 | $0.00008 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
bundled-and-mcp-turn-zero-skill-filter 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 11d 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: Bundled-and-MCP Turn-Zero Skill Filter
Domain: skill-listing Trigger: Apply when a first-turn skill listing must stay within a tight token budget, especially for subagents that cannot rely on the main thread's turn-zero discovery path. Source Pattern: Distilled from reviewed first-turn listing and token-budgeting implementations.
Core Method
When you need a small first-turn listing but the full skill registry is too large, filter down to the most intent-signaled sources first: bundled skills and user-connected MCP skills. If even that filtered set exceeds the safe listing budget, fall back again to bundled-only so the initial listing stays predictable and avoids truncation. This gives subagents a useful turn-zero surface without trying to announce the entire long tail of project, plugin, and user skills up front.
Key Rules
- Start from the full registry but explicitly filter to the smallest high-signal sources rather than trying to compress every skill source equally.
- Enforce a hard cap for the filtered listing and define a deterministic fallback when that cap is exceeded.
- Prefer bundled skills as the final fallback because they are curated, stable, and less likely to explode in count than user-connected ecosystems.
- Leave the long tail of project, plugin, and user skills to later discovery flows instead of forcing them into the turn-zero listing.
Example Application
If a spawned coding subagent needs a skill list on its first turn, offer bundled plus MCP skills while the total remains within budget. If the user has connected hundreds of MCP servers and that filtered list is still too large, show bundled skills only and rely on later discovery for the rest.
Anti-Patterns (What NOT to do)
- Do not send the full skill registry on turn zero for every subagent; large installations will hit truncation and waste prompt budget.
- Do not choose an unstable fallback that depends on arbitrary ordering; the reduced listing should remain deterministic across runs.
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.
- 11d ago First seen · 28 lines · 40 tokens per session scan A 4af4722da964
bundled-and-mcp-turn-zero-skill-filter is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 451 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.