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 user-invocable-capability-serializationgit 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/user-invocable-capability-serialization)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/user-invocable-capability-serialization"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/user-invocable-capability-serialization/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/user-invocable-capability-serialization"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/user-invocable-capability-serialization.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 | $0.00031 | $0.00564 |
| Opus 5 | $0.00015 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
user-invocable-capability-serialization 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 8d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: User-Invocable Capability Serialization
Domain: command-architecture Trigger: Use when a session-init payload or capability announcement is projecting commands, skills, or similar affordances into a user-visible surface and some registry entries are internal-only. Source Pattern: Distilled from reviewed remote-control, bridge transport, and capability-advertising implementations.
Core Method
Normalize each advertised capability into a minimal shared shape that carries its public name plus an explicit user invocable flag. At the serialization boundary, drop every entry whose flag is false, then project the survivors into the wire format. Treat omitted flags as public by default so normal commands and skills stay easy to register, while hidden or internal capabilities can opt out without special-case serializers. Applying the same rule to both slash commands and skills keeps the announced surface aligned with what a user can actually invoke and prevents helper-only entries from leaking into discovery UIs.
Key Rules
- Filter capabilities at the serialization boundary, right before projecting to plain strings or other user-facing wire fields.
- Use one shared capability shape and one shared user invocable rule across commands, skills, and similar announced surfaces so visibility policy stays consistent.
- Model hidden entries as an explicit opt-out (user invocable false) rather than scattered name-based exclusions.
- Treat missing user invocable as the common public case, but require internal helpers to set the flag explicitly so hidden behavior is intentional.
- Filter before mapping away metadata; once only names remain, the serializer can no longer distinguish public entries from internal ones.
- Let callers add stricter transport-specific filters upstream, but keep this generic user-invocable gate in the shared serializer.
Example Application
A tool registry contains normal slash commands, an internal repair command, bundled skills, and a hidden diagnostic skill used only by automation. Convert both command and skill lists into name user invocable?, run the shared filter, and serialize only the entries not marked false. The resulting init payload shows the public commands and skills, while the internal repair and diagnostic entries never appear in the announced capability surface.
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.
- 8d ago First seen · 32 lines · 31 tokens per session scan A f46b8b9082ec
user-invocable-capability-serialization is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 564 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
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.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
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.