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 linkpranay-ai/context-engineering-protocol --skill ult-autoscaffold-contentgit clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocolWrote 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/linkpranay-ai/context-engineering-protocol/ult-autoscaffold-content)<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/ult-autoscaffold-content"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/ult-autoscaffold-content.svg" alt="Measured on agentmods" 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 | $0.00212 | $0.06222 |
| Opus 5 | $0.00106 | $0.03111 |
| Sonnet 5 | $0.00042 | $0.01244 |
| Haiku 4.5 | $0.00021 | $0.00622 |
Grade A, and why
autoscaffold-content 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 8d 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ult-autoscaffold-content
Overview
ult-repo-layout can resolve where a project's What-L2 (requirements) and
How-L2 (architecture/conventions) content should live without that content
actually existing yet — a freshly-discovered repo, or a greenfield one, often
has a real, confirmed path and nothing written there. This skill fills that
gap: it writes real, honest, minimal starting content at the exact path
ult-repo-layout already resolved, so the layer stops being an empty promise
and starts being something a human can extend.
For a small repo (or a genuinely small layer target), that's one overview
file, same as Phase A — Step 4 has the exact small/large criteria. For a
large repo — many independent, non-trivial subsystems under one target
directory — one overview file undersells it, so
Phase B adds a second path: enumerate modules, rank them by real
dependency importance (not directory size) using ult-codegraph's output
when available, generate a per-module CONTEXT.md for the modules that
matter, and persist progress in a state file so a second run resumes
instead of restarting. Both paths write real, human-extensible content —
Phase B doesn't replace Phase A's honesty standard, it scales it.
This is not a subprocess the onboarding wizard (ult-cep-wizard)
shells out to. Like compiling-project-guidelines, it's invoked directly by
a human inside whichever coding agent they already have open — Claude Code,
Copilot Chat, or otherwise. When the wizard's What/How boxes are empty, its
preview card tells the user to run this skill and states the exact path the
result must land at; this skill honors that path rather than picking its
own — the output path is never left to agent discretion, so the wizard's
"Check now" button has a real path to test.
Run this:
- When
ult-cep-wizard's What or How box is empty and its card told you to run this skill - Standalone, conversationally, any time you want a starting requirements or
architecture overview for a repo that already has
ult-repo-layoutlayer paths resolved - For a large repo, any time you want per-module coverage rather than one overview file — or to continue a Phase B run that was interrupted partway through
- Standalone, any time you want a repo-wide
CODING-STANDARDS.md/TESTING-GUIDELINES.md, or an interface-boundary doc for an already-triaged module pair
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/generate-coding-standards.md 2.1 KB
- references/generate-interface-docs.md 2.2 KB
- references/generate-testing-guidelines.md 2.1 KB
- references/module-context-depth-by-tier.md 1.3 KB
- scripts/scaffold_state.py 71 KB runs code
- scripts/tests/test_scaffold_state.py 70 KB runs code
- templates/architecture-overview-template.md 2.0 KB
- templates/coding-standards-template.md 990 B
- templates/context-md-template.md 2.5 KB
- templates/interface-boundary-template.md 1.0 KB
- templates/requirements-overview-template.md 1.5 KB
- templates/testing-guidelines-template.md 1.0 KB
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.
- 8d ago First seen · 455 lines · 212 tokens per session scan A 3f2e51c796b0
autoscaffold-content is a skill published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 212 tokens to every session and 6,222 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
SDK Quickstart Writer
Generates a concise, copy-paste-ready quickstart guide for any SDK or library.
explain-codebase
Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.
First-Time User Tester
Validate the first-time user experience including onboarding flows, empty states, tutorial completion, progressive disclosure, and initial setup wizards.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
developer-marketing-playbook
Complete developer marketing playbook covering DevRel programs, documentation as marketing, API developer experience, community building, and hackathon strategy. For dev-tool founders who need to reach engineers. Follow @WeiYipei on X.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.