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 bop-clocktower/canary --skill canary-fail-fastgit clone --depth 1 https://github.com/bop-clocktower/canaryWrote 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/bop-clocktower/canary/canary-fail-fast)<a href="https://agentmods.dev/skills/bop-clocktower/canary/canary-fail-fast"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-fail-fast/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/bop-clocktower/canary/canary-fail-fast"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-fail-fast.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 | $0.00078 | $0.00633 |
| Opus 5 | $0.00039 | $0.00316 |
| Sonnet 5 | $0.00016 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
canary-fail-fast 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canary Fail-Fast
Make test failures fast (abort a broken run early) and loud (surface in the CI log + Checks, not a file). Two halves:
- Fail-fast config audit — flags the absence of
maxFailures,forbidOnly, andretriesin aplaywright.config.*. - Loud run-end digest — a terse, categorized failure summary to stdout +
::errorannotations, with a non-zero exit.
Self-contained: it bundles a minimal Playwright JSON parser and the failure categorizer, so it has no dependency on any other skill.
Fail-fast config (paste into playwright.config.ts)
export default defineConfig({
// Fail fast in CI: abort once enough has clearly broken, never on local runs.
forbidOnly: !!process.env.CI, // a stray test.only fails the build
maxFailures: process.env.CI ? 10 : 0, // stop the run after 10 failures in CI
retries: process.env.CI ? 2 : 0, // absorb flakes in CI; surface them locally
// ...your existing config
});
Invocation
# Loud failure digest from a Playwright JSON run (exits non-zero on failures):
canary skills run canary-fail-fast -- --results test-results/results.json
# Audit the fail-fast config:
canary skills run canary-fail-fast -- --config playwright.config.ts
# Both at once:
canary skills run canary-fail-fast -- \
--results test-results/results.json \
--config playwright.config.ts
# Usage and the full flag list (exits 0):
canary skills run canary-fail-fast -- --help
At least one of --results / --config is required. The digest exits 1 when
any test failed (so the CI step fails); the config audit alone never fails the
build.
CI wiring (GitHub Actions)
Run after the Playwright step with if: always() so the digest surfaces even
when the test step already failed:
- name: Run Playwright
run:
npx playwright test --reporter=json --output-file=test-results/results.json
- name: Fail-fast digest
if: always()
run: |
canary skills run canary-fail-fast -- \
--results test-results/results.json
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +3 lines 90c95200b887
- 9d ago First seen · 73 lines · 78 tokens per session scan A 9d2af0224504
canary-fail-fast is a skill published in the GitHub repository bop-clocktower/canary (4 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 633 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…