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 instructions/andyduck-ops/omp-flow/agents-mdgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWhat 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 | $0.01095 | $0.01095 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
omp-flow AGENTS.md 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — omp-flow Engineering Guide
omp-flow is a project-local workflow methodology with portable task knowledge and a small deterministic runtime kernel.
Ownership boundary
- Task meaning belongs in one Git-tracked OKF v0.2 Bundle under
.omp-flow/tasks/<task>/. - Markdown Concepts, authored indexes, prose, placement, and ordinary relative links carry purpose, investigation, provenance, requirements, design, grouping, decisions, handoffs, reviews, audits, and human approval.
- Python owns only session selection, path confinement, actor/process correlation, locks, atomic side effects, opaque operation receipts, and requested create/archive moves.
- Harnesses own models, native agent spawn, concurrency, progress, cancellation, identity, and UI.
- Platform adapters stay thin and must not reconstruct task knowledge.
Do not add a lifecycle database, exact-topology IDs, Evidence ledger, context renderer, Reference selector, Markdown parser, compatibility reader, dual write, custom dispatcher, or one-to-one replacement for a retired schema.
Workflow
task Bundle
→ brainstorm ↔ research / Reference Concepts
→ selected synthesis → PRD / Design
→ independent QbD 1 audit → linked human decision
→ authored work map and bounded work Concepts
→ independent QbD 2 audit → linked human decision
→ native implementation → linked handoff
→ independent review → linked Review Concept
→ integration / knowledge harvest / commit / archive
This is a reasoning direction, not machine phase state. Evidence can return work to framing or design. A model PASS is not human approval, and executor success is not reviewer acceptance.
Bundle contract
A new task starts with:
.omp-flow/tasks/<task>/
├── index.md # declares okf_version: "0.2"; authored navigation
├── task.md # purpose and durable task identity
└── brainstorm.md # questions, hypotheses, alternatives, reframing
Add descriptive Concepts and directories only when useful. A larger task may use research/,
reference/, context/, work/, review/, and qbd/, plus prd.md and design.md. These names
do not imply a required tier or schema. Concept bodies are free Markdown; OmpFlow does not parse
headings, list shapes, filenames, links, or arbitrary frontmatter into workflow state.
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 First seen · 114 lines · 1,095 tokens per session scan A 1b52809764bd
omp-flow AGENTS.md is an instructions file published in the GitHub repository Andyduck-ops/omp-flow (5 stars, last pushed 6d ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0055 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.