Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. 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/Koroqe/OPOS/main/.claude/skills/design-agent/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/design-agent)<a href="https://agentmods.dev/skills/koroqe/opos/design-agent"><img src="https://agentmods.dev/badge/skills/koroqe/opos/design-agent.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 | $0.00039 | $0.03361 |
| Opus 5 | $0.00019 | $0.01681 |
| Sonnet 5 | $0.00008 | $0.00672 |
| Haiku 4.5 | $0.00004 | $0.00336 |
Grade A, and why
design-agent 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-agent
When to use
Invoke when a new agent role needs to exist. Two entry points:
- Fresh role description — the user says "we need an agent for X" (e.g. "a release coordinator", "a marketing analyst").
- Formalize a backlog item — the user points at a
BACKLOG-ITEM.mdwhoseintended_targetis an agent.
Also invoked from design-process when a process design surfaces a need for an agent role that doesn't yet exist (see design-process/SKILL.md Failure modes).
The skill is INTERACTIVE: it produces a proposal, iterates with the user, and only writes the agent file on explicit user approval. The human is the approval gate.
Inputs
role_description— free-text description of the new agent's responsibilities + scope + decisions it should make + what it does NOT do. Required if nobacklog_item_pathis supplied.backlog_item_path— OPTIONAL. Path to aBACKLOG-ITEM.mdwhoseintended_targetis an agent. When supplied, the item's frontmatter seeds the proposal; the item is flipped tostate: designedwith adesigned_as: <new-agent-path>field at the end.
Registry pass (v0.13)
When drafting the tools: ladder AND the role's external-access needs: read company/resources/REGISTRY.md. Grants derive from DECLARED resources, never invention — a role needing an access no entry covers gets a "requires acquisition" line in the proposal (naming the /acquire-resource request to file) instead of a fabricated tool. If the role's core duty depends on a per-machine resource (machines: bound), say so in the proposal so the human knows where the agent can actually operate.
Steps
- Lessons pass + provenance duty (v0.11, applies to every run). Before designing: read the company's
kind: lessonbacklog items (glob**/backlog/*.md, filter frontmatterkind: lesson) whosemistake_class/root_cause_targetmatches this skill or the artifact class it produces, plus this skill's ownhistory/entries with openproposed_deltas; apply every matching constraint to the draft and LIST the applied lessons in the proposal so the human sees the loop working. When writing the artifact: stamp provenance — frontmatterderived_from: <template>@<framework-version>+designed_by: <this-skill>@<its version>(framework version =.copier-answers.yml_commit; in the framework repo itself use the current release tag); charter files get the equivalent HTML comment stamp at file end.
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.
- 2d ago Changed 1427ce1907ce
- 6d ago First seen · 128 lines · 39 tokens per session scan A 62f8818dd1be
design-agent is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 3,361 once invoked, about $0.0002 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
super-evolve
Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.