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 prevent-continuation-stop-hook-messaginggit 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/prevent-continuation-stop-hook-messaging)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/prevent-continuation-stop-hook-messaging"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/prevent-continuation-stop-hook-messaging/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/prevent-continuation-stop-hook-messaging"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/prevent-continuation-stop-hook-messaging.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 | $0.00560 |
| Opus 5 | $0.00016 | $0.00280 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
prevent-continuation-stop-hook-messaging 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: Prevent Continuation Stop Hook Messaging
Domain: tool-orchestration
Trigger: Use when stop hooks prevent continuation so you can surface a consistent attachment plus a summary notification that downstream UI/logging consumes.
Source Pattern: Distilled from reviewed tool-loop and result-shaping patterns.
Core Method
Capture every hook progress update while the stop-hook generator runs, track how many hooks fired, preserve per-hook command and prompt details, then attach later timing/error data to the matching hook entries. When a hook asks to prevent continuation, emit a machine-readable hook_stopped_continuation attachment with the hook name, tool use ID, and stop reason, then synthesize the concise StopHookSummary message that surfaces counts, errors, and whether the turn was blocked. This keeps UI banners, transcript log notifications, and verbose hooks in sync, with a single reusable pattern that works whenever any hook stops the turn.
Key Rules
- Gather
hookInfosfromprogressattachments (command, prompt, duration) andhookErrorsfrom non-blocking or blocking attachments so you can summarize each hook’s outcome. - Emit the
hook_stopped_continuationattachment exactly whenpreventContinuationbecomes true, supplyingtoolUseID, hook name, and the stop reason so log processors and tool-tracking pipelines get a structured signal. - After the generator completes, call
createStopHookSummaryMessagewith counts, accumulated info, the prevented flag, and whether actual output already streamed; this keeps UI, transcript, and notification consumers aligned on the stop reason. - Send the notification that references
stop-hook-erroronly when there are errors so verbose transcript/ctrl+o viewers know the details exist. - Keep the machine-readable attachment and summary message in lockstep so telemetry and UI never disagree about whether continuation was blocked and why.
Example Application
When the Stop hook intercepts a red team command that would delete infrastructure, emit the hook_stopped_continuation attachment with hookEvent: 'Stop', then send the summary message so the REPL banner shows “Stop hook prevented continuation: ” while telemetry records how many hooks fired and what errors occurred.
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 · 33 tokens per session scan A c123658bf0c9
prevent-continuation-stop-hook-messaging 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 560 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.
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.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
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.