time-gap-cache-expiry-microcompact

time-gap-cache-expiry-microcompact is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 38 tokens per session (444 once invoked), scanned A, original, MIT.

A cache-maintenance rule for long idle gaps: when the prompt cache is likely cold, it clears old tool-result text before the next request instead of editing the warm cache.

In plain words
What is it for?
It is for managing context and cached session state in assistants that may sit idle between requests.
Why use it?
It avoids cache operations that no longer apply and treats the upcoming full rewrite as intentional cleanup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for managing context and cached session state in assistants that may sit idle between requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact
Install

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.

Any agent
npx skills add ychampion/cskill-agents --skill time-gap-cache-expiry-microcompact
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for time-gap-cache-expiry-microcompact

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/time-gap-cache-expiry-microcompact)
Your own site
<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.

agentmods 80×15 button for time-gap-cache-expiry-microcompact

Your own site · 80×15
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 0c978a291b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

agents/claude-code/skills/time-gap-cache-expiry-microcompact/SKILL.md · 29 lines

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.

Read the full file on GitHub · 29 lines

Changes

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.

  1. 8d ago First seen · 29 lines · 38 tokens per session scan A 0c978a291b24

Subscribe to this mod's changes

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.