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 main-thread-only-cache-editinggit 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/main-thread-only-cache-editing)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/main-thread-only-cache-editing"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/main-thread-only-cache-editing/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/main-thread-only-cache-editing"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/main-thread-only-cache-editing.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 | $0.00027 | $0.00440 |
| Opus 5 | $0.00014 | $0.00220 |
| Sonnet 5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
main-thread-only-cache-editing 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.
What it actually says
SKILL: Main Thread Only Cache Editing
Domain: context-management
Trigger: Use when cached microcompact runs and you must prevent subagents or forks from writing cache edits that the main thread shares.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Only perform cache-editing microcompactions when the executing query source is the main thread (repl_main_thread or unspecified). This avoids contaminating shared cachedMCState with tool results that belong to background runs like session-memory compact, prompt suggestion, or other forks. The guard also ensures the cached MC path is never triggered in non-ANT builds that disable the feature altogether.
Key Rules
- Wrap the cached microcompact logic with
isMainThreadSource(querySource)so only canonical queries can edit the global cache. - Gate the entire block behind
feature('CACHED_MICROCOMPACT')to keep the functionality out of builds that do not support it. - The guard must look at
querySource.startsWith('repl_main_thread')rather than strict equality so styled prompt contexts still match. - Reread the guard whenever adding new query sources to ensure no rogue forks affect cache edits.
- Keep the cached state initializations and edits strictly within this guarded branch so other modules cannot mutate
cachedMCStateunexpectedly.
Example Application
When a main-thread REPL session hits the cached microcompact trigger, the guard passes, allowing registerToolResult and createCacheEditsBlock to run. Forked agents such as session memory or prompt suggestion skip this block entirely, leaving the global cache untouched.
Anti-Patterns (What NOT to do)
- Do not let background slices access or mutate
cachedMCState; they should always defer to the main thread’s editing path. - Do not drop the guard when adding new caching features; the main-thread-only contract must remain explicit.
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 · 29 lines · 27 tokens per session scan A 97888932751e
main-thread-only-cache-editing is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 440 once invoked, about $0.0001 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.