omp-flow: Skill for Claude Code

.agents/skills/omp-flow-implement/SKILL.md

omp-flow-implement is a skill for Claude Code, Codex from Andyduck-ops/omp-flow. It costs 29 tokens per session (712 once invoked), scanned A, original, MIT.

A controlled workflow for implementing one defined piece of work from an OMP-Flow task bundle and returning a linked handoff. It requires the task, role, allowed code area, completion conditions, and required approvals or receipts.

In plain words
What is it for?
Use it to turn an approved design into code, execute it, verify the result, and report evidence or conflicts back to the coordinator.
Why use it?
It prevents an implementer from taking work outside its assigned boundary or skipping required verification and handoff steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is Andyduck-ops/omp-flow's own configuration. It tells Claude Code and Codex how to work on omp-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything omp-flow configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Andyduck-ops/omp-flow/main/.agents/skills/omp-flow-implement/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Andyduck-ops/omp-flow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for omp-flow-implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-implement/github.svg)](https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-implement)
Your own site
<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.

agentmods 80×15 button for omp-flow-implement

Your own site · 80×15
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 5592b1e02763, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.agents/skills/omp-flow-implement/SKILL.md · 66 lines

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.

  1. Read the work Concept first. Follow only useful links to design, decisions, sources, and relevant existing code/tests.
  2. Restate the bounded objective, output boundary, done conditions, and verification before editing.
  3. Preserve unrelated work and follow existing project patterns.
  4. 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.
  5. 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.
  6. 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.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 9d ago Changed · +6 lines · +6 tokens per session 5592b1e02763
  2. 2mo ago Changed · +1 lines f9eb8900f87f
  3. 2mo ago First seen · 59 lines · 23 tokens per session scan A 60f422abd00e

Subscribe to this mod's changes

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.

Related

omp-flow-implement compared with skills from other repositories

omp-flow-implement next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
omp-flow-implementAndyduck-ops/omp-flowSkill69d agoMITA29Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code