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 mitodl/agent-kit --skill add-canary-journeygit clone --depth 1 https://github.com/mitodl/agent-kitWrote 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/mitodl/agent-kit/add-canary-journey)<a href="https://agentmods.dev/skills/mitodl/agent-kit/add-canary-journey"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/add-canary-journey/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/mitodl/agent-kit/add-canary-journey"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/add-canary-journey.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 | $0.00116 | $0.03642 |
| Opus 5.5 | $0.00046 | $0.01457 |
| Sonnet 5.5 | $0.00023 | $0.00728 |
| Haiku 4.5 | $0.00012 | $0.00364 |
Grade A, and why
add-canary-journey 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 15d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Canary Journey or Property
Repository: mitodl/ol-infrastructure.
Every unqualified path below is relative to that checkout.
When to use
Someone wants a new end-to-end user journey watched continuously, or a new web property brought into the canary fleet.
To run what you write, use the run-canary-locally skill. This skill is about
what to write and which files to touch.
Read these rather than working from memory — they are authoritative and this skill deliberately does not duplicate them:
canaries/AGENTS.md— the non-negotiables and the locator/assertion rules.canaries/README.md— what a canary is, what does not belong, and the deployment runbook.specs/<property>/README.md— that property's ranked journey table and content dependencies.- ADR 0011 — why the specs live in this repo.
First: is this a canary at all?
A canary is not a PR test. The two have opposite failure economics: a PR test should be strict, while a canary must fail only when something is genuinely wrong for users, because its only output is a red Concourse build that a human is expected to trust.
| Belongs here | A journey a real user takes, that we want to know about within minutes of it breaking in a deployed environment. |
| Does not belong here | Anything gating a pull request. That lives in the application's own repo against its own dev stack. |
Assert on the journey completing, not on the content it finds along the way. A canary asserting on CMS copy or a course price goes red every time an editor changes a word, and reds that mean nothing are how a canary trains its audience to ignore it.
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.
- 15d ago Changed a51a27b3540e
- 25d ago First seen · 310 lines · 116 tokens per session scan A a71a3be8d9e9
add-canary-journey is a skill published in the GitHub repository mitodl/agent-kit (5 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 116 tokens to every session and 3,642 once invoked, about $0.0005 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 2026-09-23.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
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.
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…