orchflows AGENTS.md

Repository instructions for orchflows, a library that coordinates main agents and helper agents across several layers. They define its architecture, terminology, shared rules, research skill, and required validation commands.

In plain words
What is it for?
Use them when changing orchflows, its documentation or rules, the super-research item, routing behavior, or validation and test tooling.
Why use it?
They help contributors follow the project's boundaries and run the checks needed for normal and same-process compatibility.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/danmcinerney/orchflows/agents-md
Clone the repo
git clone --depth 1 https://github.com/DanMcInerney/orchflows

Made for: Codex, OpenCode.

Per session 453 This file is loaded in full into every session.
When invoked 453 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00453 $0.00453
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash 4c797613e35e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchflows 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.

AGENTS.md · 48 lines

What it actually says

Repository guidance

The canonical orchflows source: a four-tier library for orchestrator > subagent work. ARCHITECTURE.md maps boundaries, ownership, dependency direction; docs/vocabulary.md owns every library term and a pack's craft cell its domain's; rules/ owns cross-cutting law, under rules/visibility.md §3. The Constitution in docs/library-review.md requires every sentence here.

Routing, the state sink and the friction law are the host block's — templates/host-block.md, installed at ~/.orchflows/host-block.md. From this checkout the friction command is python scripts/friction.py "<what happened>" "<what was expected or missing>", same sink, same flags.

  • Project-scope custom item super-research — manual invocation only, keyless read-only acquisition — at .orchflows/skills/super-research/SKILL.md.

Required checks

Through this host's verified interpreter (uv run --no-project python; bare python is a Windows Store stub; Python 3.9 or newer, install.py's floor):

python tools/validate.py python tools/run_tests.py # one process per module python tools/run_serial_compat.py # selected same-process lane python install.py --dry-run git diff --check

python tools/run_required.py runs the five, cached by tree; a gate passes --no-cache. While working, python tools/run_tests.py --scope <changed-paths> runs only the affected shards; the five decide the tip. Adding or removing tests regenerates the manifest with python tools/run_serial_compat.py --write-manifest.

Selected routinely checks cross-module coupling; exhaustive python -m unittest discover -s tests -v stays scheduled/manual and pre-release; green here is provisional until the .github/workflows/checks.yml matrix agrees — python tools/preflight.py replays it, docstrings own the rest.

Serial compatibility

tools/serial-compat-policy.md defines the routine lane and fallback.

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. 2d ago First seen · 48 lines · 453 tokens per session scan A 4c797613e35e

Subscribe to this mod's changes

orchflows AGENTS.md is an instructions file published in the GitHub repository DanMcInerney/orchflows (51 stars, last pushed 2d ago), licensed MIT. It adds 453 tokens to every session, about $0.0023 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 2026-08-30.

Related

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens