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 slash-command-skill-classification-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/slash-command-skill-classification-filter)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/slash-command-skill-classification-filter"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/slash-command-skill-classification-filter.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00574 |
| Opus 5 | $0.00022 | $0.00287 |
| Sonnet 5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
slash-command-skill-classification-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 4d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Slash-Command Skill Classification Filter
Domain: Command Architecture Trigger: Use when a slash-command picker or human-facing skill list must be derived from a larger prompt-command registry without exposing builtin, undocumented, or wrongly sourced commands. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Build the slash-command skill surface as a curated filtered view over the broader command registry instead of treating every prompt command as a skill. Require each surfaced entry to be prompt-shaped, non-builtin, and backed by clear human-readable metadata such as a summary or trigger sentence. Admit only an approved set of source classes such as installed skills, bundled skills, and trusted plugins. If a command is intentionally user-invocable but not model-invocable, keep it visible in the human-facing picker while still excluding it from automatic model execution.
Key Rules
- Start from the full command registry, then derive a dedicated slash-command skill subset with explicit admission rules rather than sharing a looser generic listing.
- Keep the filter scoped to prompt-type commands so execution semantics match the slash-command skill surface.
- Exclude builtin commands from this surface even if they are prompt-shaped; builtin command discovery belongs to a different UX path.
- Require descriptive metadata such as a summary or trigger sentence before a command can appear, so the user never sees opaque entries with no guidance.
- Restrict source admission to a controlled allowlist like
skills,plugin, andbundledinstead of assuming every external prompt command is a skill. - Preserve an override path for manual-only commands when they should remain user-discoverable even though the model is not allowed to invoke them automatically.
Example Application
If an editor assistant builds a skills palette from all registered prompt commands, first remove builtins, then keep only entries with clear description metadata, and finally admit only bundled skills, installed skill packs, approved plugin commands, plus a manual-only deployment helper that users may run themselves. The result is a human-facing palette that stays informative and intentionally curated without hiding useful manual commands.
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.
- 4d ago First seen · 31 lines · 44 tokens per session scan A ea9a6ab44e35
slash-command-skill-classification-filter is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 574 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
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.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
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.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.