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 skip-skill-discovery-on-skill-expansiongit 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/skip-skill-discovery-on-skill-expansion)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/skip-skill-discovery-on-skill-expansion"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skip-skill-discovery-on-skill-expansion/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/skip-skill-discovery-on-skill-expansion"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skip-skill-discovery-on-skill-expansion.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 | $0.00042 | $0.00457 |
| Opus 5.5 | $0.00017 | $0.00183 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
skip-skill-discovery-on-skill-expansion 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 1mo 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: Skip Skill Discovery on Skill Expansion
Domain: command-surfaces
Trigger: Apply when generated or expanded skill text must pass through the attachment pipeline for parsing, but it is not fresh user intent and must not trigger discovery queries.
Source Pattern: Distilled from reviewed command-surface and listing-control patterns.
Core Method
Separate "text being inspected" from "text expressing user intent." When a pipeline reuses the attachment extractor on expanded SKILL.md content or other generated prompts, pass an explicit skip flag so the discovery subsystem stays off while the rest of the attachment logic still runs. This preserves useful secondary parsing such as @-mentions without paying for recursive or misleading skill-discovery calls on machine-generated text. The guard should live exactly where discovery would otherwise be attached so the expensive path is impossible to trigger accidentally.
Key Rules
- Run skill discovery only for genuine user-authored input, not for expanded skill files, generated prompts, or other agent-produced text.
- Use an explicit option or context flag to disable only the discovery branch, leaving the rest of the attachment pipeline active.
- Keep the gate adjacent to the discovery attachment construction so future refactors cannot bypass it unintentionally.
- Treat large injected documents as especially high risk; one missing gate can turn a single skill invocation into repeated expensive discovery calls.
Example Application
If a slash command loads a 100 KB skill specification and then reuses the normal attachment extractor to resolve @-mentions inside it, pass skipSkillDiscovery: true. The extractor still parses mentions, but it does not launch another round of skill-discovery queries against the generated document body.
Anti-Patterns (What NOT to do)
- Do not run discovery on expanded SKILL.md content or other generated prompts; that mistakes system-produced text for user demand.
- Do not disable the entire attachment pipeline just to suppress discovery; you still want legitimate parsing such as file mentions and other lightweight attachments.
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.
- 1mo ago First seen · 28 lines · 42 tokens per session scan A 725a53ef4c52
skip-skill-discovery-on-skill-expansion is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 457 once invoked, about $0.0002 per session on Opus 5.5. 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
static
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.
cleanup
Find duplicates, dead links and untagged items in a saved library and propose what to do about each.
antigravity-cli
Use Antigravity CLI as a subagent. Lets the main agent prompt Antigravity CLI from the terminal in headless mode with the agy command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Antigravity CLI, when a task needs a second independent agent, or when a plan…
outcome-run
Run one action in an outcome-loop folder. Use when the user wants to execute the outcome loop, start with Superdense reward maintenance, choose one action on a lever, create runs/ /work.md and learnings.md, or use prior outcomes to improve a real-world metric.
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
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.