bundled-and-mcp-turn-zero-skill-filter

bundled-and-mcp-turn-zero-skill-filter is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 40 tokens per session (451 once invoked), scanned A, original, MIT.

A rule for choosing which skills appear in an agent's first-turn skill list. It prefers bundled skills and skills supplied through connected MCP services, then reduces the list further if it is too large.

In plain words
What is it for?
Filtering a full skill registry for subagents or other first-turn contexts with limited space. It provides a bundled-plus-MCP list when possible and a bundled-only fallback when necessary.
Why use it?
It keeps the initial skill listing within a strict token budget and avoids truncating the information an agent sees at startup. The selection is deterministic, so the result is predictable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Filtering a full skill registry for subagents or other first-turn contexts with limited space. It provides a bundled-plus-MCP list when possible and a bundled-only fallback when necessary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter
Install

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.

Any agent
npx skills add ychampion/cskill-agents --skill bundled-and-mcp-turn-zero-skill-filter
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bundled-and-mcp-turn-zero-skill-filter

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/bundled-and-mcp-turn-zero-skill-filter)
Your own site
<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.

agentmods 80×15 button for bundled-and-mcp-turn-zero-skill-filter

Your own site · 80×15
<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>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 4af4722da964, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

agents/claude-code/skills/bundled-and-mcp-turn-zero-skill-filter/SKILL.md · 28 lines

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.

Read the full file on GitHub · 28 lines

Changes

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.

  1. 11d ago First seen · 28 lines · 40 tokens per session scan A 4af4722da964

Subscribe to this mod's changes

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.