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/files-publish/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/files-publish)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/files-publish"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/files-publish/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/files-publish"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/files-publish.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 | $0.00037 | $0.02059 |
| Opus 5.5 | $0.00015 | $0.00824 |
| Sonnet 5.5 | $0.00007 | $0.00412 |
| Haiku 4.5 | $0.00004 | $0.00206 |
Grade A, and why
preview-env-files-publish 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env files-publish
Conversation sandbox, session branch ctxpipe/chat/{conversationId}/1, GitHub pull request. The agent decides when to commit and push to that branch: when the user asks, or when it finishes a task (its system prompt recommends committing then), with semantic commit messages. The conversation header offers Sync (for anything not yet committed, including the user's own edits), Create PR (keeps every commit; no squash), and Show PR. Chat never pushes the default branch. Harness write policy applies (see run-setup). Flow format: run-setup.
If Settings shows Read-only, publish controls are hidden: SKIP(no-fixture) the write flows, not FAIL.
FP-1 Browse conversation files
Requires CHAT-1 (a conversation) and a hydrated Workspace 1. Steps
- On the conversation URL, open Files.
- Single-click a file; double-click another; use Hide tree / Show tree.
Expect (UI) the tree shows the workspace repository as this conversation sees it; single-click previews with the tree staying open; double-click opens a closeable named tab (pane=file:<path>); Hide tree / Show tree appear only after a file is selected.
Expect (backend) GET …/conversations/{id}/files/tree and …/files/blob return 200 (the sandbox starts or resumes if needed).
Budget 2 s / 8 s to the tree (plus up to 3 s if the sandbox must resume).
Evidence FP-1-1.png; trace of the tree request.
FP-2 Create and save a file in a conversation
Requires FP-1; Workspace Writable.
Steps
- In Files, click New file. Enter the one-segment name
note-{run-id}.mdand click Create. The Name field does not accept a/, and Create stays disabled until the name is valid. To make a file in a folder, make the folder first (New folder), then right-click it and choose New file. - Click the editor and wait about 500 ms. Type one line that names
run-idand the origin. In a script, set a key delay of at least 30 ms. A script that types at once after the click loses the first characters. - Click Save (autosave runs 10 s after the last key press, or when the editor loses focus). Wait until Save is disabled again.
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 · 97 lines · 37 tokens per session scan A 90f8cec6fb1d
preview-env-files-publish is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,059 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…
tdd
Enforces red-green-refactor TDD cycle with atomic commits per phase. Used when implementing features, fixing bugs, or when tests should drive the design.
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.