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-based-microcompact-triggergit 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-based-microcompact-trigger)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/time-based-microcompact-trigger"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/time-based-microcompact-trigger/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-based-microcompact-trigger"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/time-based-microcompact-trigger.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 | $0.00424 |
| Opus 5 | $0.00016 | $0.00212 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
time-based-microcompact-trigger 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: Time-Based Microcompact Trigger
Domain: context-management
Trigger: Apply when the interval since the last assistant response exceeds the threshold and cached microcompact cannot run.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Measure the minutes since the last main-thread assistant message, compare it to gapThresholdMinutes, and only fire when the configured trigger is enabled and the caller is the main thread. When triggered, keep the last keepRecent tool results and content-clear the rest by replacing their content with the [Old tool result content cleared] marker. Log the elapsed gap, tokens saved, and retained count so operators can tune the gap threshold.
Key Rules
- Require a specific
querySource(main thread) before firing so external helpers do not misinterpret delays as triggers. - Return
nullunless the gap exceeds the threshold, ensuring callers only run the clearing logic when necessary. - Always keep at least one tool result so the model retains some recent state after the purge.
- Reset cached microcompact state and notify cache deletion after the clearing to keep downstream cache tracking in sync.
- Emit analytics and debug logs describing the gap, tokens saved, and how many tools were cleared.
Example Application
When a session sits idle longer than gapThresholdMinutes, apply this trigger to replace outdated tool results with [Old tool result content cleared], log the 12-minute gap, and still leave the last tool result so future summaries have some fresh context.
Anti-Patterns (What NOT to do)
- Do not run this trigger for non-main-thread sources; the clearing assumes global cache edits.
- Do not drop all cached tools (keep at least one), or the next turn loses every tool reference and can exceed budget on the first message.
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 · 29 lines · 33 tokens per session scan A c56690a5e311
time-based-microcompact-trigger 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 424 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.