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 cache-warm-before-cache-only-fanoutgit 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/cache-warm-before-cache-only-fanout)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/cache-warm-before-cache-only-fanout"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-warm-before-cache-only-fanout/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/cache-warm-before-cache-only-fanout"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-warm-before-cache-only-fanout.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 | $0.00033 | $0.00414 |
| Opus 5 | $0.00016 | $0.00207 |
| Sonnet 5 | $0.00007 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
cache-warm-before-cache-only-fanout 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 9d 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: Cache Warm Before Cache-Only Fanout
Domain: extensions-mcp
Trigger: Apply when one authoritative load populates caches that several cheaper readers depend on, and parallel reads would race the warm path.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
Run the expensive authoritative loader first, let it materialize and warm the shared caches, and only then fan out cache-only readers in parallel. This preserves a single source of truth for cache population while still recovering parallelism for the cheap derived reads. The result is deterministic: every downstream reader sees the same fresh state without each one redoing install or clone work.
Key Rules
- Identify which loader actually populates the canonical cache and make it run before any cache-only consumers.
- Keep derived readers cache-only; they should assume the warm path already handled the expensive side effects.
- Use parallel fanout only after the warm step resolves successfully.
- Document why the ordering matters so later refactors do not collapse everything back into a premature
Promise.all. - Let the warm path own cache population and reuse; do not make each consumer silently fall back to heavyweight work.
Example Application
If an extension refresh must first scan and clone any missing plugins before separate readers build the command list and agent list, await the full plugin load once, then run command extraction and agent extraction in parallel against the warmed cache.
Anti-Patterns (What NOT to do)
- Do not launch cache-only readers in parallel with the warm path if they can read stale manifests or miss newly materialized content.
- Do not duplicate heavy install logic in each derived loader just to hide ordering bugs.
- Do not remove the sequencing comment when the dependency is subtle; future maintainers will reintroduce the race.
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.
- 9d ago First seen · 30 lines · 33 tokens per session scan A a82fd1c55b4e
cache-warm-before-cache-only-fanout is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 414 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.
Other skills, from other repositories
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
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.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press
Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…
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.