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/graph/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/graph)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/graph"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/graph/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/graph"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/graph.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 | $0.00729 |
| Opus 5.5 | $0.00000 | $0.00292 |
| Sonnet 5.5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
preview-env-graph 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env graph
This Workspace's projection, not an org-wide graph. Hydrate must be ready (HYD-1). Harness is PASS. Flow format: run-setup.
GRAPH-1 Pane loads
Requires HYD-1. Steps
- Open
{BASE_URL}/{orgSlug}/ws/{workspace1Slug}?pane=graph(the composer URL is enough).
Expect (UI) pane=graph in the URL, the Graph tab selected, and a painted canvas (nodes and edges) or an honest empty state. Empty after ready with no "derived graph unavailable" copy is a PASS (sparse projection). The copy derived graph unavailable is a FAIL.
Expect (backend) GET /{orgSlug}/api/v1/workspaces/{workspace1Slug}/graph returns 200 (503 is a FAIL: the graph store or projection is down); the projection has 4 WorkspaceKnowledgeUnit nodes and 11 WorkspaceSignal edges, told apart by their predicate property: 7 LINKS_TO from the template's relative links and 4 claim edges (DEPENDS_ON, IMPLEMENTED_IN, OWNS, PART_OF). Edges are not typed relationships named after the predicate.
Budget 3 s / 10 s, pane open to canvas painted.
Evidence GRAPH-1-1.png; HTTP status; trace of the graph request.
GRAPH-2 Select a node
Requires GRAPH-1 with at least one node (else SKIP(no-fixture)).
Steps
- Click a node.
- If the inspector offers a source path, open it.
Expect (UI) an inspector or drawer shows a label; the source path opens Files (pane=file:… or pane=files). If the URL gains ?node=, it stays.
Expect (backend) none beyond the graph GET.
Budget 1 s / 3 s, click to inspector.
Evidence GRAPH-2-1.png.
GRAPH-3 Reload on the graph URL
Requires GRAPH-1. Steps
- With
pane=graphin the address bar, hard-reload; then open the same URL in a new tab.
Expect (UI) the shell renders, the Graph pane mounts, and no blank page or crash screen appears (the canvas is client-only; server rendering must not break). The browser console has no uncaught error from the pane.
Expect (backend) the document request returns 200; the graph GET follows once.
Budget 5 s / 15 s, reload to canvas or empty state.
Evidence GRAPH-3-1.png; console excerpt on failure.
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 · 47 lines · 0 tokens per session scan A fba1e340426b
preview-env-graph is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 729 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 2026-10-21.
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…
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
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.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.