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 scalarian/oh-my-codex --skill architectgit clone --depth 1 https://github.com/scalarian/oh-my-codexWrote 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/scalarian/oh-my-codex/architect)<a href="https://agentmods.dev/skills/scalarian/oh-my-codex/architect"><img src="https://agentmods.dev/badge/skills/scalarian/oh-my-codex/architect.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 | $0.00021 | $0.00503 |
| Opus 5 | $0.00010 | $0.00251 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
architect 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Purpose
Use $architect to reduce risk before implementation starts. This mode exists to answer: what must change, what must not break, and what is the least dangerous path through the codebase?
Use When
- the change crosses multiple subsystems
- a new interface, storage contract, or public API is involved
- several implementations look plausible
- brownfield context is weak and guessing would be expensive
Do Not Use When
- the task is a narrow bug fix with obvious scope
- a plan already names the exact files, contracts, and verify steps
- the only open question is product intent, not system shape
Execution Policy
- Read the active
.omx/plans/*.mdfiles and current repo entry points first. - Prefer discovered repo truth over architectural taste.
- Preserve existing invariants unless there is a concrete reason to change them.
- Produce one recommended path, not a brainstorm dump.
- Call out the exact points where the user must make a business or migration decision.
Workflow
- Inspect the likely entry points, downstream side effects, and sibling implementations.
- Update
.omx/plans/brownfield-map.mdwith boundaries, risky subsystems, and must-preserve behavior. - Identify the core contract changes:
- data shape
- interface surface
- lifecycle/state transitions
- verification surface
- Compare 2-3 viable approaches only when the choice is real.
- Pick the recommended path and explain:
- why it fits the existing repo
- what it avoids
- what would make it fail
- Hand off to
$planor$executorwith concrete file targets and verify hooks.
Deliverables
- updated
.omx/plans/brownfield-map.md - recommendation in
.omx/research/summary.mdor active plan notes - explicit invariants and risk notes for the next execution pass
Stop Conditions
Stop and ask the user when:
- the best path requires a destructive migration
- two options are both valid but optimize for different product outcomes
- the repo contains conflicting patterns and you cannot infer the intended winner
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 · 69 lines · 21 tokens per session scan A 4d1260686395
architect is a skill published in the GitHub repository scalarian/oh-my-codex (73 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 503 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".