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-implement/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-implement)<a href="https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-implement"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-implement/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-implement"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-implement.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 | $0.00029 | $0.00712 |
| Opus 5.5 | $0.00012 | $0.00285 |
| Sonnet 5.5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
omp-flow-implement 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMP-Flow Implement
Required Inputs
Fail closed unless all are available:
- task Bundle root;
- role and bounded objective;
- descriptive work entry Concept;
- allowed code scope and handoff output Concept;
- actor ID and opaque dispatch receipt;
- completed predecessor receipt when the operation requires one.
Procedure
Main/coordinator alone dispatches, correlates receipts, records human calibration, and chooses transitions. A dispatched Implementer performs only the bounded implementation and assigned handoff; it does not dispatch, govern, calibrate, transition, or reinterpret coordinator clauses. It returns the approved Design to practice through code, execution, and real verification, and reports contradictory evidence as a Design-return signal rather than special-case reality to preserve Design authority.
- Read the work Concept first. Follow only useful links to design, decisions, sources, and relevant existing code/tests.
- Restate the bounded objective, output boundary, done conditions, and verification before editing.
- Preserve unrelated work and follow existing project patterns.
- Implement only what the work Concept requires. Report a design contradiction instead of
silently redesigning the system. When settling a minor local choice inside the approved
boundary, record
Decision: <choice> — <rationale> — <consequence if wrong>in the handoff. - Run focused verification and broader checks required by the brief. Verify against usable end-to-end behavior (and judge new tests against two imagined edits: breaking behavior fails the test, restructuring internals keeps it passing); report environment-blocked checks explicitly as unverified rather than disguising a type-check as full verification.
- Inspect the final diff for scope, generated files, debug residue, and accidental state edits. Update a Task index or linked map only when the implementation adds or changes a useful discoverable link.
When a Work/Handoff Concept benefits from provenance, authors may use optional OKF v0.2 prose
(sources, generated, verified, status, stale_after). Link the source Task, checkpoint or
commit, producer actor, and verification evidence where known. These fields are descriptive only;
absence does not invalidate a handoff, and they never replace the opaque operation receipt or a
different-actor Review.
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 · +6 lines · +6 tokens per session 5592b1e02763
- 2mo ago Changed · +1 lines f9eb8900f87f
- 2mo ago First seen · 59 lines · 23 tokens per session scan A 60f422abd00e
omp-flow-implement is a skill published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 712 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-implement compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omp-flow-implementAndyduck-ops/omp-flow | Skill | 6 | 9d ago | MIT | A | 29 | 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 |