A local browser wizard for discovering and resolving a project's directory layout. It runs only on localhost and guides you through the repository's configured layers and locations.

It is for initializing or reviewing repository layout and resolving pending directory assignments.

It gives engineers a visual way to inspect or fix layout choices without manually working through configuration files.

cep-wizard — Command for GitHub Copilot by linkpranay-ai

Install

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.

Clone the repo

git clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocol

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard/github.svg)](https://agentmods.dev/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard)

Your own site

<a href="https://agentmods.dev/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard"><img src="https://agentmods.dev/badge/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard"><img src="https://agentmods.dev/badge/commands/linkpranay-ai/context-engineering-protocol/ult-cep-wizard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 949 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00121	$0.00949
Opus 5	$0.00060	$0.00475
Sonnet 5	$0.00024	$0.00190
Haiku 4.5	$0.00012	$0.00095

Measured today against content hash d39ad8a55ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cep-wizard 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 today.

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.

.github/prompts/ult-cep-wizard.prompt.md · 61 lines

What it actually says

Read and follow the skill at .github/skills/ult-cep-wizard/SKILL.md.

Hand-authored, not generator-owned: unlike most prompts in this directory, this one is not mechanically derivable from frontmatter alone. This skill isn't "chat message in, one response out" — it's "run a terminal command, then interact in a browser for a session" — so the steps below exist to carry that shape explicitly.

When invoked directly by an engineer:

Run python .github/skills/ult-cep-wizard/scripts/wizard_server.py <repo_root> in a terminal, passing the real project root explicitly (never inferred). Unlike Phase 0/1, the repo does not need to have run ult-repo-layout init/discover first — wizard_preflight.py now only requires ult-repo-layout to be installed; if it reports a missing-dependency error, that's the one thing to resolve (usually re-running install.ps1/install.sh without a narrow --only flag) before re-running step 1.
Open the one-time exchange URL the server prints in a browser (or hand it to the engineer if you're running headless/over SSH — the server never assumes it can open a browser itself). The link is single-use and expires after 30 minutes of idle time.
The page shows exactly one of four screens depending on the repo's current state — see references/wizard-onboarding-state-machine.md for the full table:
- Layout broken — validate_layout.py's own validation is currently failing; resolve what it reports (by hand, or by asking the engineer to) before anything else here is meaningful.
- Let's find this repo's layout — no discovery artifact yet; click Run Discover (a real, in-process call to discover_layers.run_discovery() — safe, scans and proposes, writes nothing into context-config.yaml itself).
- Decisions — walk each PENDING/STAGED field with the engineer (confirm/skip/disable/acknowledge/pick-a-directory via the picker below), then click Apply once every field is resolved — this is the only step that commits into context-config.yaml, via ult-repo-layout's own confirm_layers.py.
- Steady state — everything already confirmed; walk the four boxes (What, How, Guidelines, Trip-wire) and the directory picker with the engineer. For any box showing an empty-case content-scaffolding card, that card is a preview prompt for you (the agent) to act on in a separate turn — the wizard never writes content itself.
If a dismissible banner appears mentioning ult-repo-layout init hasn't run, that's informational only (affects Guidelines defaults) — it never blocks any of the above; point the engineer at /ult-repo-layout init if they want to clear it, then click Done to re-check.
Stop the server (Ctrl+C in the terminal) when the session is done. Nothing is left running in the background.

Do not reach for this skill for headless or CI-only validation — call ult-repo-layout's discover/confirm-layers/validate_layout.py --validate directly for that instead.

Changes

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.

today First seen · 61 lines · 121 tokens per session scan A d39ad8a55ef4

Subscribe to this mod's changes

cep-wizard is a command published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 949 once invoked, about $0.0006 per session on Opus 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 2026-09-08.

Project management ai-agents ai-coding-assistants code-graph context-engineering cursor onboarding project-layout utility wizard

cep-wizard

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

taskstoissues

team

say

gaai-status

gaai-daemon

gaai-deliver