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 agentmods add skills/koroqe/opos/design-processnpx skills add Koroqe/OPOS --skill design-processgit 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-process)<a href="https://agentmods.dev/skills/koroqe/opos/design-process"><img src="https://agentmods.dev/badge/skills/koroqe/opos/design-process.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 | $0.00033 | $0.03551 |
| Opus 5 | $0.00016 | $0.01775 |
| Sonnet 5 | $0.00007 | $0.00710 |
| Haiku 4.5 | $0.00003 | $0.00355 |
Grade A, and why
design-process 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-process
When to use
Invoke when a new repeatable job needs to be formalized as a process. Two entry points:
- Fresh job description — the user says "we need a process for X." No prior backlog item.
- Formalize a backlog item — the user points at a
BACKLOG-ITEM.mdand says "design a process from this."
The skill is INTERACTIVE: it produces proposals, iterates with the user, and only writes files on explicit user approval. The human user is the approval gate; there is no draft staging or formal review queue.
Inputs
job_description— free-text description of the work to be formalized. Required if nobacklog_item_pathis supplied.backlog_item_path— optional path to aBACKLOG-ITEM.mdto use as additional input. When supplied, the item's frontmatter (title,owner,intended_target, labels) seeds the design; the item itself is converted tostate: designedand gains adesigned_as: <new-skill-path>field at the end.
Draft mode (v0.12 — the non-interactive builder path)
/design-process --draft --from <backlog-item-path> runs the design END-TO-END with no human in the loop and writes a proposal bundle instead of live files — the double-gated shape that makes overnight self-building safe (bundle is inert text; adoption is a human Confirm via /adopt-proposal; scheduling, if any, is a second human gate at registration):
- Steps 1–3 run normally (read framework, understand the job from the backlog item's Goal/Acceptance, enumerate depts).
- Step 4 consultations run in lite form: consult only the single owning dept's lead (one
consult-agentcall), noting in the bundle which consultations a full run would have added. - Steps 5–6 draft the complete
SKILL.md+PROCESS.mdpair exactly as usual (lessons pass + provenance stamps included). - Steps 7–8 (present + iterate) are SKIPPED — their human judgment moves to adoption.
- Step 9 writes the bundle to
<owning-dept>/backlog/proposals/<date>-<slug>/(SKILL.md, PROCESS.md, and a PROPOSAL.md cover sheet:intended_placement:(the step-5 placement decision, e.g.departments/<dept>/.claude/skills/<name>/— REQUIRED; adoption reads it from here), the source backlog item, consultations run/skipped, lessons applied, open questions) — NEVER into any.claude/skills/path. Update the source backlog item:state: drafted, Runs-log row. - Steps 10–11 (backlinks, history entry) run normally; the history entry notes
mode: draft.
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.
- today Changed b8166ab42a12
- 4d ago First seen · 133 lines · 33 tokens per session scan A 3cd7db42ed0e
design-process is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 3,551 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…
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
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.
captions-overlay
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether…