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 time-gap-cache-expiry-microcompactgit 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/time-gap-cache-expiry-microcompact)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact/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/time-gap-cache-expiry-microcompact"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact.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 | $0.00038 | $0.00444 |
| Opus 5 | $0.00019 | $0.00222 |
| Sonnet 5 | $0.00008 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
time-gap-cache-expiry-microcompact 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Time-Gap Cache-Expiry Microcompact
Domain: compaction Trigger: Apply when a long gap since the last assistant response implies the prompt cache has expired and cache-editing no longer makes sense. Source Pattern: Distilled from reviewed session memory, compaction, and context-budgeting implementations.
Core Method
Detect when the cache is effectively cold by comparing the idle gap against a time-based microcompact threshold. If the gap is too large, skip cache-editing entirely and proactively clear old tool-result content before the next request, because the full prefix will be rewritten anyway. Reset any cached microcompact state and suppress false-positive cache-break warnings so the cold-cache rewrite is treated as an intentional maintenance step.
Key Rules
- Evaluate the idle gap only for explicit main-thread requests; analysis-only calls without a real query source should not trigger time-based compaction.
- Short-circuit before cache-editing when the gap exceeds the configured threshold, because cache edits assume a warm server cache.
- Reset shared cached-microcompact state after the content clear so stale registered tool IDs do not leak into later turns.
- Notify cache-break detection that the upcoming drop in cache reads is expected, not a genuine regression.
- Suppress compact warnings on successful time-gap cleanup so users do not get duplicate noise for the intentional clear.
Example Application
If a user leaves a conversation idle for long enough that the server prompt cache is gone, clear old read/shell tool results before the next turn rather than trying to attach cache-edit instructions. The next request pays one clean rewrite cost and starts from a consistent compacted state.
Anti-Patterns (What NOT to do)
- Do not attempt cache edits after a long idle gap; those edits assume cached server state that no longer exists.
- Do not leave cached microcompact state intact after a time-gap clear; stale tool registrations will poison the next edit cycle.
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 · 29 lines · 38 tokens per session scan A 0c978a291b24
time-gap-cache-expiry-microcompact is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 444 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.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
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…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.