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 autocompact-circuit-breakergit 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/autocompact-circuit-breaker)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/autocompact-circuit-breaker"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/autocompact-circuit-breaker/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/autocompact-circuit-breaker"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/autocompact-circuit-breaker.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 | $0.00028 | $0.00381 |
| Opus 5 | $0.00014 | $0.00191 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
autocompact-circuit-breaker 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 11d 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: Autocompact Circuit Breaker
Domain: context-management
Trigger: Apply when autocompact failures repeat and the service must stop retrying to avoid API storms.
Source Pattern: Distilled from reviewed session memory, compaction, and context-budgeting implementations.
Core Method
Track consecutive autocompact failures via the caller-provided auto compact tracking state. After each failure, increment the counter, log a warning once the configured limit is reached, and return the updated count instead of throwing. The loop uses this counter to skip further auto-compact attempts as long as the limit is exceeded, effectively acting as a circuit breaker that keeps doomed sessions from flooding the service.
Key Rules
- Add one to the failure counter on every exception (unless it’s a user abort).
- When the counter reaches the policy limit, log the breaker trip so telemetry reveals the gap.
- Return was compacted false plus consecutive failures so callers can persist the new state.
- Use the counter to skip auto-compact early on future turns rather than re-running the failed path.
- Reset the counter on a successful compaction so normal behavior resumes.
Example Application
After three consecutive failures hitting the context limit, auto compact if needed stops retrying, logs circuit breaker tripped, and the tracker causes the next turn to skip compaction until a successful run resets the counter.
Anti-Patterns (What NOT to do)
- Don’t let the controller keep retrying with the same broken context; the breaker exists to keep it quiet.
- Don’t swallow failure logs — future debugging relies on the warning emitted when the limit trips.
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.
- 11d ago First seen · 29 lines · 28 tokens per session scan A e10f67964769
autocompact-circuit-breaker is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 381 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 2026-08-30.
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.