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 me-cedric/agent-compass --skill e2egit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/e2e)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/e2e"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/e2e/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/me-cedric/agent-compass/e2e"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/e2e.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 | $0.00000 | $0.00690 |
| Opus 5.5 | $0.00000 | $0.00276 |
| Sonnet 5.5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
e2e 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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
e2e
Run each suite through the registry. Read the result file. Do not guess the cause of a failure.
Run a suite
- Run
ac run --list. Look for the suite name. - If the suite is not there, add an entry to
agent-compass.commands.jsonfirst. Never invent a command. - Run
ac run <name>. Add--timeout <seconds>for a long suite.
{
"e2e": {
"web": "npx playwright test",
"smoke": { "cmd": "npx playwright test --grep @smoke", "timeout": 600 },
"mobile": "maestro test .maestro"
}
}
The registry runs a command without a shell. A pipe, a redirect, a glob or a $VAR is an error.
Put a filter in a quoted argument.
Read the result
ac run writes .agents/runs/<timestamp>-<name>/:
result.jsonhasexitCode,timedOut,durationMs, the last 100 lines intail, and the paths injunitandhtml.output.loghas the full output. Secret-like lines are redacted.
- Read
tailfirst. Then read thejunitXML for the names of the failed tests. - Open the
htmlreport path for traces and screenshots. - Fix one failure at a time. Run only that test again, with a registry entry that has the filter.
- A test that fails on one run and passes on the next is flaky. Find the cause. Do not add a retry or a sleep.
Playwright and its test agents
Set up the agents once with npx playwright init-agents. Use the option that matches your client (--help lists them).
- The planner explores the app and writes a test plan.
- The generator turns the plan into test files.
- The healer runs the failed tests and edits them.
Review every healer edit as a code change. Read the diff before you accept it. Reject an edit that removes or weakens an assertion, adds a sleep, widens a selector, or skips a test. A failing test can show a real bug in the app. Fix the app, not the test.
Screenshots
Create and update toHaveScreenshot baselines only on the pinned CI image. That is the Playwright Docker image at the version in package.json.
A baseline from a laptop differs in fonts and rendering. Never commit one.
Review each changed baseline image as a code change.
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.
- 9d ago Changed · -50 tokens per session f2fa72d54e04
- 10d ago First seen · 67 lines · 50 tokens per session scan A ab2b59bb0280
e2e is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 690 tokens. 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 2026-10-18.
Other skills, from other repositories
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders…
android-emulator
Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.