docflow AGENTS.md

A set of instructions for docflow, a project that stores and routes knowledge for AI coding agents in organized Markdown documentation.

In plain words
What is it for?
Working on docflow while keeping its product specifications, technical documents, plans, decisions, and changelog up to date.
Why use it?
It tells an agent which documents to read and where to record product details, technical decisions, plans, reviews, and shipped changes.

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/medadembha/docflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/MedAdemBHA/docflow

Made for: Codex, OpenCode.

Per session 307 This file is loaded in full into every session.
When invoked 307 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 $0.00307 $0.00307
Opus 5 $0.00153 $0.00153
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 2d ago against content hash ceb1dee8c184, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docflow 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 · 35 lines

What it actually says

Agent Guide

Repo use docflow.

Start here:

  1. Read docs/README.md.
  2. Read the summary and latest entry in the newest file under docs/changelog/. Open older entries only when the task needs deeper history.
  3. Then code.

New feature flow:

  1. Add/update product-spec/ for WHAT.
  2. Add/update specs/ for HOW.
  3. Add/update plans/features/ for status + feature log.
  4. Append shipped work to current changelog/(mmm-yy).md.

Route by question:

  • WHAT feature do: docs/product-spec/
  • HOW built: docs/specs/
  • WHY chose it: docs/decisions/
  • Rules / conventions: docs/references/
  • Planned / in progress: docs/plans/
  • Bugs / audits / quality: docs/reviews/
  • What shipped: docs/changelog/

Rules:

  • Follow docs/NAMING.md.
  • Keep docs/README.md updated. Durable doc go there.
  • changelog/ append-only. Add current month if missing. Do not rewrite old months except factual fix.
  • If work change behavior, architecture, decision, plan, or known issue, update docs.
  • Prefer docs before code for behavior, architecture, decisions, roadmap, known issues.
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 · 35 lines · 307 tokens per session scan A ceb1dee8c184

Subscribe to this mod's changes

docflow AGENTS.md is an instructions file published in the GitHub repository MedAdemBHA/docflow (41 stars, last pushed 17d ago), licensed MIT. It adds 307 tokens to every session, about $0.0015 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.