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 cache-safe-stop-hook-snapshottinggit 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/cache-safe-stop-hook-snapshotting)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/cache-safe-stop-hook-snapshotting"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-safe-stop-hook-snapshotting/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/cache-safe-stop-hook-snapshotting"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cache-safe-stop-hook-snapshotting.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 | $0.00420 |
| Opus 5 | $0.00016 | $0.00210 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
cache-safe-stop-hook-snapshotting 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: Cache-Safe Stop-Hook Snapshotting
Domain: context-management
Trigger: Apply when end-of-turn hooks need to persist enough state for follow-up helpers, but background forks must not overwrite the main session snapshot.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Build one structured hook context at turn end, then persist a cache-safe snapshot only when the query source belongs to the main interactive session or the SDK control path. This gives downstream helpers a stable resume surface while preventing side agents and background forks from clobbering shared state with their own narrower contexts. The snapshot gate lives outside optional prompt-suggestion features so every consumer that depends on the shared state still gets it.
Key Rules
- Create the snapshot from the full stop-hook context, not ad hoc fragments, so later consumers see the same system, user, and tool state.
- Gate snapshot persistence to the authoritative query sources such as
repl_main_threadandsdk. - Keep forked or background agents out of the shared snapshot path; their contexts are partial and will pollute resume behavior.
- Decouple snapshotting from optional background features so state persistence remains available even when prompt suggestions are off.
Example Application
If a REPL turn finishes and /btw or another side-question helper may run next, save a cache-safe snapshot from the main turn’s hook context. If a background memory extractor reaches the same stop-hook code, skip the snapshot so the main session state remains authoritative.
Anti-Patterns (What NOT to do)
- Do not let every subagent write to the same cache-safe snapshot location; later helpers will resume from polluted or incomplete context.
- Do not tie snapshot persistence to an unrelated feature flag when multiple consumers depend on it.
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 · 28 lines · 33 tokens per session scan A a4f704587cdb
cache-safe-stop-hook-snapshotting 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 420 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 2026-08-30.
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.