agentmods.dev

docflow AGENTS.md

Repository instructions for docflow, a tool that adds documentation-led working practices and architecture decision records to software projects. An architecture decision record is a short document explaining an important technical choice.

In plain words
What is it for?
Use them when working on docflow itself or its shared skills for Claude Code, Claude Cowork, pi, Codex, and OpenCode.
Why use it?
They give coding agents the repository structure and rules they must follow when creating, changing, shipping, or reviewing these records and plans.

Instructions file for CodexOpenCode

10 27d ago A scan 1,680 tokens original MIT
View the source file EvolveHQ/docflow
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/evolvehq/docflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/EvolveHQ/docflow

Made for: Codex, OpenCode.

Per session 1,680 This file is loaded in full into every session.
When invoked 1,680 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 $0.01680 $0.01680
Opus 5 $0.00840 $0.00840
Sonnet 5 $0.00336 $0.00336
Haiku 4.5 $0.00168 $0.00168

Measured 2d ago against content hash 38af1cf87185, 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 · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents working in this repository.

What this repository is

docflow is a multi-target plugin that scaffolds (and retrofits) ADR-driven, documentation-led conventions into other repositories, plus a set of lifecycle skills to author, queue, ship, and audit ADRs. It ships the same plugins/docflow/skills/ directory to five coding agents — Claude Code, Claude Cowork, pi, Codex, and OpenCode — from one source (see ADR 0015). This repo now also dogfoods its own conventions: the ADR catalogue, plan queue, and _agent/ coordination below describe how docflow itself is built and maintained.

Repository structure

  • plugins/docflow/skills/ — the product. bootstrap/ (with templates/) plus the lifecycle skills (new-adr, new-plan, ship-item, add-convention, audit, brainstorm, agent-wave, rollup). This is what gets installed. One source for every target.
  • plugins/docflow/.claude-plugin/plugin.json — Claude Code / Cowork plugin manifest; plugins/docflow/.codex-plugin/plugin.json — Codex.
  • .claude-plugin/marketplace.json + .agents/plugins/marketplace.json — the marketplaces (root), each pointing at ./plugins/docflow.
  • package.json — pi manifest (pi.skills → ./plugins/docflow/skills)
    • npm metadata.
  • README.md, USAGE.md, docs/ — user-facing documentation.
  • adr/0000-template.md — canonical ADR template.
  • adr/NNNN-<kebab-slug>.md — one ADR per decision, contiguous numbering, no gaps. These describe docflow itself. (The optional domains/ grouping layer the product offers is not enabled in this repo.)
  • INDEX.md — table regenerated from every ADR's metadata block.
  • CONVENTIONS.md — authoring rules (read before editing anything).
  • plan/todo/NNNN-<slug>.md — pending work, lower numbers run first.
  • plan/done/<YYYY-MM-DD>-<slug>.md — shipped work, chronological.
  • _agent/ — coordination: ROLES.md, WORKLOG.md, CURRENT_FOCUS.md, HANDOFF.md, prompts/.
  • scripts/verify.mjs — the static verify gate (manifests + version sync, skill structure + parity, ADR catalogue + INDEX sync, ADR-privacy leak scan).
  • evals/ — behavioural eval harness: deterministic assertions plus subagent-driven end-to-end skill runs (release gate, not per-push).

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 1,680 tokens per session scan A 38af1cf87185

Subscribe to this mod's changes

docflow AGENTS.md is an instructions file published in the GitHub repository EvolveHQ/docflow (10 stars, last pushed 27d ago), licensed MIT. It adds 1,680 tokens to every session, about $0.0084 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.

DocumentsPlanningWriting and docsadrarchitecture-decision-recordsclaude-codeclaude-code-plugindocumentation
Related

Other instructions, from other repositories

adr copilot-instructions.md

Instructions for zircote-plugins/adr, covering copilot instructions, project overview, key components, plugin structure and development guidelines.

zircote-plugins/adr · 256 tokens

keep-the-why AGENTS.md

Instructions for oliver-zehentleitner/keep-the-why, covering agents.md and working conventions (no why needed, just follow these).

oliver-zehentleitner/keep-the-why · 255 tokens

adrkit AGENTS.md

Instructions for mbeacom/adrkit, covering adrkit, visual adr graph, inbound @adr markers (v0.5.0: explain, check, and ci), the spec kit extension (packages/adapters/spec-kit) and adr queue.

mbeacom/adrkit · 5,493 tokens

codebase-intel CLAUDE.md

Instructions for MutharasuArchunan13/codebase-intel, covering codebase intel — project claude.md, project overview, tech stack, architecture and module responsibilities.

MutharasuArchunan13/codebase-intel · 1,248 tokens

adrkit copilot-instructions.md

Instructions for mbeacom/adrkit, covering adrkit — github copilot and github copilot specifics.

mbeacom/adrkit · 310 tokens

adrkit CLAUDE.md

Instructions for mbeacom/adrkit, covering adrkit — claude code and claude code specifics.

mbeacom/adrkit · 263 tokens