Borrowing it
Nothing to install: this file belongs to Andyduck-ops/omp-flow. 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/Andyduck-ops/omp-flow/main/.agents/skills/omp-flow-decompose/SKILL.mdgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWrote 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/andyduck-ops/omp-flow/omp-flow-decompose)<a href="https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-decompose"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-decompose/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/andyduck-ops/omp-flow/omp-flow-decompose"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-decompose.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 | $0.00036 | $0.00627 |
| Opus 5.5 | $0.00014 | $0.00251 |
| Sonnet 5.5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
omp-flow-decompose 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMP-Flow Decompose
Preconditions
- The Bundle links the approved PRD, Design, applicable audit, and human QbD 1 decision.
- The assignment identifies the Bundle root, design entry, bounded output area, actor ID, and receipt.
Procedure
Main/coordinator alone dispatches, correlates receipts, records human calibration, and chooses transitions. After linked human QbD 1 approval, a dispatched Architect performs only the bounded Decompose responsibility and assigned work outputs; it does not dispatch, govern, calibrate, transition, or reinterpret coordinator clauses. It maps the approved Design into bounded, independently reviewable work Concepts and an authored prose execution view, without inventing approval or encoding a machine DAG.
- Identify the smallest independently implementable and reviewable work items. Fold scaffolding and docs into the deliverable that needs them.
- Write one descriptive work Concept per item with objective, in/out scope, useful linked inputs,
allowed code/output boundary, neighbor interface contracts (
Consumes/Producesexact signatures when work items interact), done conditions, verification command with expected output, and expected handoff Concept. - Specify decisions, not code transcripts: state exact file paths, signatures, pinned values, and concrete test assertions (including implied edge/failure inputs from the Design) so the implementer can write one unambiguous implementation; include a code body only for a non-obvious algorithm that the signature and assertions do not determine.
- Author
work/index.mdwhen it improves discovery. Use prose and grouping to communicate normal ordering, parallel work, alternatives, and relevant follow-up. - Link only useful Concepts. Do not generate a closed context manifest or require link closure.
- Give every work item a descriptive path; do not encode dependencies or dispatch receipts in filenames.
- Verify coverage from each PRD requirement to work, check signature consistency across neighbor Work Concepts, and check proportion: if a Work Concept is dominated by implementation bodies, replace the bodies with signatures and test assertions.
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.
- 9d ago Changed · +7 lines · +7 tokens per session 05a3609d6383
- 2mo ago Changed · -1 lines 6d452d60cb49
- 2mo ago First seen · 49 lines · 29 tokens per session scan A f54f89d55a9c
omp-flow-decompose is a skill published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 627 once invoked, about $0.0001 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.
omp-flow-decompose compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omp-flow-decomposeAndyduck-ops/omp-flow | Skill | 6 | 9d ago | MIT | A | 36 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |