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 lifecycle-scoped-resource-cleanupgit 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/lifecycle-scoped-resource-cleanup)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/lifecycle-scoped-resource-cleanup"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/lifecycle-scoped-resource-cleanup/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/lifecycle-scoped-resource-cleanup"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/lifecycle-scoped-resource-cleanup.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 | $0.00043 | $0.00409 |
| Opus 5 | $0.00022 | $0.00204 |
| Sonnet 5 | $0.00009 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
lifecycle-scoped-resource-cleanup 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: Lifecycle-Scoped Resource Cleanup
Domain: lifecycle-management Trigger: Each agent run, regardless of outcome, must unwind resources reserved for its lifetime without assuming the parent session will later re-claim them. Source Pattern: Distilled from reviewed subagent orchestration, isolation, and lifecycle implementations.
Core Method
Treat each child agent run as one lifecycle with a single unconditional cleanup path. After the run finishes, fails, or aborts, execute a predictable teardown sequence that disconnects per-agent integrations, unregisters hooks and watchers, clears temporary caches and staging state, removes agent-owned bookkeeping records, and stops any background jobs started on that agent’s behalf. Keep cleanup scoped to resources owned by that one agent so parent and sibling sessions remain untouched.
Key Rules
- Run lifecycle cleanup from one unconditional
finally/defer path so success, failure, and cancellation all converge on the same teardown logic. - Guard optional cleanup steps with the same feature flags that created those resources in the first place.
- Remove agent-owned records entirely rather than leaving empty placeholders in shared state maps.
- Stop background jobs, hooks, and watches before the parent session can reuse the same identifiers or workspaces.
Example Application
When a background workflow agent aborts due to timeout, these cleanup routines close MCP sockets, remove hooks that would fire on subsequent subagents, and kill orphaned shell loops so the terminal remains responsive.
Anti-Patterns
- Do not perform cleanup only on the happy path or only in
catch; missing the unconditional cleanup path leaves clients, hooks, or jobs running forever. - Do not leave temporary caches or agent-owned state records behind after completion; stale state can leak memory and corrupt later runs.
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 · 28 lines · 43 tokens per session scan A a5b43d168d84
lifecycle-scoped-resource-cleanup is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 409 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.
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.