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 SetraTheXX/Codex-Engineering-Workflow-Pack --skill prototypegit clone --depth 1 https://github.com/SetraTheXX/Codex-Engineering-Workflow-PackWrote 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/setrathexx/codex-engineering-workflow-pack/prototype)<a href="https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/prototype"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/prototype/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/setrathexx/codex-engineering-workflow-pack/prototype"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/prototype.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 | $0.00049 | $0.00881 |
| Opus 5.5 | $0.00020 | $0.00352 |
| Sonnet 5.5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
prototype 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 1mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
Use a prototype to answer a question quickly before changing production behavior.
A prototype is temporary. It should have a clear question, success criteria, and exit decision.
Read First
Inspect relevant context:
docs/agents/domain.mddocs/agents/test-commands.mdCONTEXT.md- relevant ADRs under
docs/adr/ - existing UI routes, components, modules, tests, or scripts near the idea
If setup docs are missing, infer local conventions from the repo and say what is unknown.
Choose Prototype Type
Pick one:
Logic Prototype
Use when the question is about:
- state transitions,
- business rules,
- validation behavior,
- data transformations,
- edge cases,
- algorithm shape.
Typical shape: a small local script, REPL-friendly module, or isolated route through existing public functions.
UI Prototype
Use when the question is about:
- layout,
- interaction flow,
- component composition,
- navigation,
- visual variants,
- user feedback states.
Typical shape: a temporary route, page, story, or local-only component variant.
If the type is ambiguous, recommend one and explain why.
Workflow
1. Define The Experiment
State:
- question being answered,
- prototype type,
- audience or actor,
- success criteria,
- constraints,
- what will not be tested.
If success criteria are unclear, ask the user before creating files.
2. Inspect Local Conventions
Find where a temporary prototype would fit without confusing production code.
Look for:
- existing scripts,
- playground routes,
- storybook stories,
- examples directories,
- test fixtures,
- local-only dev pages.
Do not invent a new convention when the repo already has one.
3. Propose Path And Command
Before writing, propose:
- files to create,
- files to touch,
- how to run it,
- how it will be marked temporary,
- how it will be removed or promoted.
Ask for approval before creating files.
4. Build Small
When approved:
- keep state local unless persistence is the experiment,
- avoid production integration by default,
- mark temporary files clearly,
- expose relevant state in the UI or console,
- skip polish that does not answer the question,
- avoid new dependencies unless approved.
What ships with it
3 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.
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.
- 1mo ago First seen · 176 lines · 49 tokens per session scan A 579c03438ce6
prototype is a skill published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed 28d ago), licensed MIT. It adds 49 tokens to every session and 881 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pdlc-ui-design-pro
A UI/UX design workflow for projects that use a PRD, or product requirements document, as the starting point. It checks the PRD and related design documents before creating or updating design-system guidance.
pdlc-ui-design
A user-interface and user-experience design guide that turns an existing product requirements document into a page and interaction plan. A PRD is a document describing what a product or feature must do.
brainstorming
Refines rough ideas into approved designs before code.
frappe-doctype-design
Frappe DocType creation and form UX guidance. Use when creating, reviewing, or redesigning DocTypes, including field choice, tabs, sections, columns, required fields, naming, child tables, and form usability.
fireworks-tech-graph
A generator for technical diagrams that exports them as SVG and PNG images. It is intended for architecture, data-flow, flowchart, sequence, agent, memory, and concept-map diagrams.
draw-io-diagram-generator
Use when creating, editing, or generating draw.io diagram files (.drawio, .drawio.svg, .drawio.png). Covers mxGraph XML authoring, shape libraries, style strings, flowcharts, system architecture, sequence diagrams, ER diagrams, UML class diagrams, network topology, layout strategy, the hediet.vscode-drawio VS Code…