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 namespace-resolved-skill-preloadinggit 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/namespace-resolved-skill-preloading)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/namespace-resolved-skill-preloading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/namespace-resolved-skill-preloading/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/namespace-resolved-skill-preloading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/namespace-resolved-skill-preloading.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 | $0.00026 | $0.00389 |
| Opus 5 | $0.00013 | $0.00195 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
namespace-resolved-skill-preloading 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 6d 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.
What it actually says
SKILL: Namespace-Resolved Skill Preloading
Domain: agentic-loop Trigger: Apply when an agent definition lists startup skills by friendly name but the registry may store those skills under plugin-qualified names. Source Pattern: Distilled from reviewed startup-skill preload and namespaced-command resolution implementations.
Core Method
Resolve each configured skill through a layered lookup: direct match, plugin-prefixed match, then suffix match across namespaced registrations. Reject missing or non-prompt commands with warnings instead of silently swallowing them, then load the remaining skills concurrently and inject their contents as explicit startup messages with metadata that shows what was preloaded. This makes startup capability bootstrapping both flexible and auditable.
Key Rules
- Use layered resolution rather than assuming one naming convention, because plugin ecosystems mix bare names and fully qualified names.
- Validate that the resolved command is prompt-based before preloading it into the transcript.
- Load valid skills concurrently so startup does not serialize on independent skill fetches.
- Materialize preloaded skills as visible transcript messages with loading metadata instead of hiding them inside prompt assembly.
Example Application
If a plugin agent declares skills: [review, deployment-checks] but the registry stores them as plugin-x:review and plugin-x:deployment-checks, resolve them through the namespace fallback chain, preload both, and surface their startup messages so the UI shows what context was injected.
Anti-Patterns (What NOT to do)
- Do not fail the whole startup path because one configured skill is missing; warn and keep preloading the valid ones.
- Do not bury preloaded skill content in a hidden prompt string; operators need to see which startup skills were applied.
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.
- 6d ago First seen · 28 lines · 26 tokens per session scan A c6bd215c4512
namespace-resolved-skill-preloading is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 389 once invoked, about $0.0001 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.
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.