Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ctxpipe-ai/ctxpipe/main/.agents/skills/preview-env/resilience/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/resilience)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/resilience"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/resilience/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/ctxpipe-ai/ctxpipe/resilience"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/resilience.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 | $0.00026 | $0.01000 |
| Opus 5.5 | $0.00010 | $0.00400 |
| Sonnet 5.5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
preview-env-resilience 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env resilience
Last area: it disturbs the target. Harness is PASS; run it after the other areas. Flow format: run-setup.
RES-1 Backend restart mid-chat (gated-restart-ok)
Requires flag restart-ok (a human or the run may restart the backend: local stop and start pnpm dev; preview Railway restart-service or redeploy of the backend, allowed on pr-280 only per the write policy); CHAT-2.
Steps
- Send a long-answer prompt in the Workspace 1 conversation; while it streams, restart the backend.
- Watch the UI until the backend is back, then reload the conversation URL.
- Send a short follow-up.
Expect (UI) during the outage the conversation shows an inline connection or stream error with a way to continue (never a blank page); after the restart the transcript shows every message persisted before the cut; the follow-up is answered on the same conv_…. Uncertain: whether the interrupted turn completes after reconnect or ends in a clear error; record which. A rolling deploy may land a tool call on a replica that is not running the turn (known limit, ticket 02).
Expect (backend) the interrupted chat_runs row ends in a terminal state (not running forever); the conversation's sandbox is reattached or recreated from its session branch (workspace_sandbox_instances), not duplicated.
Budget 90 s / 3 min, restart to a working follow-up.
Evidence RES-1-1.png (outage state), RES-1-2.png (recovered); traces before and after; run states.
RES-2 Worker sleep and wake (preview-only)
Requires preview mode; Workspace 1 hydrated; a commit pushed to the workspace repository after the wait (HYD-3 steps).
Steps
- Leave the preview untouched for 4 minutes (preview workers idle-exit after about 180 s).
- Check the worker service status (Railway MCP).
- Push a commit to the workspace repository, then reload the Workspace.
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.
- 4d ago First seen · 51 lines · 26 tokens per session scan A 3d484216597f
preview-env-resilience is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,000 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
browser-journey-test
Validate user stories by simulating real user journeys in a live browser against deployed application. Activate after implementation to verify actual user experience against acceptance criteria, not just code logic.
sidekick-audit
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
sidekick-test
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.