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/connectors/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/connectors)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/connectors"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/connectors/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/connectors"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/connectors.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 | $0.00031 | $0.02032 |
| Opus 5.5 | $0.00012 | $0.00813 |
| Sonnet 5.5 | $0.00006 | $0.00406 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
preview-env-connectors 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env connectors
/{orgSlug}/connectors. Types: GitHub, Confluence, Linear, Notion, Slack, PagerDuty. Content connectors fetch provider content and hand it to a typed mirror job that commits it into a Workspace repository (linear/, notion/, slack/, confluence/, pagerduty/, github/); scope is a <connector>/config.yaml reviewed in a pull request. Harness is PASS. Flow format: run-setup.
Provider flows (CON-3 to CON-7) depend on the ready-for-human test workspaces in run-setup: each is SKIP(needs-human) until the user supplies them and a human is at the OAuth consent screen. A flow that completes OAuth also needs flag live-oauth and this origin's OAuth and webhook URLs registered with that provider (hosted previews: uncertain; ask before assuming).
Health chips on a closed card: Connected · Not yet connected · Couldn't load · Sync failed · Config PR failed · Checking. Connected means Postgres plus UI health and a finished initial mirror, not Slack capture or a merged config PR by itself.
CON-1 Catalog
Requires ONB-3. Steps
- Open
{BASE_URL}/{orgSlug}/connectors; open Add connection. - Open each card once; do not click Remove.
Expect (UI) the six providers are offered (GitHub first); GitHub reads Connected; each open card shows Workspace / scope / sync destination (or a connect or setup action); with no connector the empty state shows.
Expect (backend) GET of the org connections returns the GitHub connections row (con_*).
Budget 3 s / 10 s, navigation to cards visible.
Evidence CON-1-1.png; trace of the connections request.
CON-2 First screen of each wizard
Requires CON-1. Steps
- For Slack, Linear, Notion, Confluence, and PagerDuty, open Add connection to the provider's first screen only; close the dialog.
Expect (UI) each first screen renders (hosted: no self-host credential steps; local self-host: the register-OAuth-app step); closing leaves no half-created card.
Expect (backend) no connections row is created.
Budget 1 s / 3 s per dialog.
Evidence CON-2-1.png per provider.
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.
- 3d ago Changed 5639bd3f7658
- 4d ago First seen · 95 lines · 31 tokens per session scan A 65873ac1923c
preview-env-connectors is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 2,032 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.