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 layered-command-cache-invalidationgit 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/layered-command-cache-invalidation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/layered-command-cache-invalidation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/layered-command-cache-invalidation/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/layered-command-cache-invalidation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/layered-command-cache-invalidation.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 | $0.00032 | $0.00515 |
| Opus 5 | $0.00016 | $0.00258 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
layered-command-cache-invalidation 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.
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Layered Command Cache Invalidation
Domain: Command Architecture
Trigger: Use when commands, skills, or search indexes are cached in layers and a refresh must make newly added or removed entries visible immediately.
Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Treat cache invalidation as a stack problem, not a single-cache problem. When one memoized command view is built on top of other memoized loaders, clear the outer derived cache alongside the inner source caches in the same invalidation path. Otherwise the outer memoized function can keep returning its old result without ever touching the refreshed inner layers, so callers never observe the update.
Key Rules
- Map the dependency order of cached views: raw sources, merged registries, derived command subsets, and any search or index layer built on top.
- Clear every cache layer that can satisfy requests from its own memoized result; if an outer layer can return without recomputing, it must be invalidated explicitly.
- Centralize the clears in one helper that runs whenever dynamic command or skill state changes, so mutation paths cannot forget a derived cache.
- Keep the invalidation contract close to the layering comment or dependency declaration, because partial clears often look correct in code review while remaining behavioral no-ops.
- Prefer one named reset entrypoint for the whole stack over scattered per-cache clears; callers should ask for a fresh command surface, not reason about cache topology.
Example Application
An agentic IDE may memoize the merged command registry, memoize the slash-command projection derived from that registry, and memoize a local skill-search index built on top of both. When a new skill is installed, invalidate all three layers together. Clearing only the registry caches is insufficient if the search index still serves its own cached snapshot.
Anti-Patterns (What NOT to do)
- Do not clear only the innermost loaders and assume outer memoized views will notice; cached derived layers can bypass recomputation entirely.
- Do not let each mutation site clear an ad hoc subset of caches; one missed caller leaves stale command surfaces in place.
- Do not describe a partial clear as a refresh if users can still hit an old search index, command palette, or tool registry afterward.
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 · 30 lines · 32 tokens per session scan A b619578f2710
layered-command-cache-invalidation is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 515 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.
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.