What is SkillFlow AGENTS.md?

Repository instructions for SkillFlow, a Go project that organizes coding-agent skills, prompts, integrations, documentation, and architecture into clearly scoped directories. A repository is a project’s version-controlled collection of code and related files.

Adding Go components, maintaining the skill and prompt catalogs, updating architecture or configuration documentation, and following the project’s directory and documentation rules.

They enforce where source code and documentation must live, preventing the project root from becoming disorganized. They also require documentation and configuration to stay synchronized with the implementation.

SkillFlow AGENTS.md — Instructions file by shinerio

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/shinerio/skillflow/agents-md

Clone the repo

git clone --depth 1 https://github.com/shinerio/SkillFlow

Made for: Codex, OpenCode.

Per session 4,744 This file is loaded in full into every session.

When invoked 4,744 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.

Model	Per session	Once invoked
Fable 5	$0.04744	$0.04744
Opus 5	$0.02372	$0.02372
Sonnet 5	$0.00949	$0.00949
Haiku 4.5	$0.00474	$0.00474

Measured 2d ago against content hash a2d7adc57341, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SkillFlow 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 · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 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 when working with this repository.

Directory Organization Rule - MANDATORY

The root directory must contain no Go source files. All code lives in clearly scoped subdirectories:

/ (project root - no .go files here)
  go.mod, go.sum
  Makefile
  AGENTS.md (→ CLAUDE.md symlink)
  README.md, README_zh.md
  contributing.md, contributing_zh.md
  LICENSE, .gitignore, .github/
  changelog/
  chats/
  docs/
    agents/
      skill_directory.md
      memory_directory.md
    architecture/
      README.md
      README_zh.md
      overview.md
      overview_zh.md
      contexts.md
      contexts_zh.md
      layers.md
      layers_zh.md
      use-cases.md
      use-cases_zh.md
      runtime-and-storage.md
      runtime-and-storage_zh.md
    features.md
    features_zh.md
    config.md
    config_zh.md
    plans/
    superpowers/
  core/
    config/
    platform/
    shared/
    orchestration/
    readmodel/
    skillcatalog/
      app/
      domain/
      infra/
    promptcatalog/
      app/
      domain/
      infra/
    agentintegration/
      app/
      domain/
      infra/
    skillsource/
      app/
      domain/
      infra/
    backup/
      app/
      domain/
      infra/
  cmd/
    skillflow/
      main.go
      app.go, app_*.go
      adapters.go, providers.go, events.go, version.go
      process_*.go
      tray_*.go
      window_*.go
      single_instance_*.go
      wails.json
      build/
      frontend/

Rules:

Never add .go files to the project root.
New backend business code must go under a bounded context in core/<context>/app, core/<context>/domain, or core/<context>/infra.
Cross-context write coordination belongs in core/orchestration/.
Cross-context read composition belongs in core/readmodel/.
Pure technical capabilities with no business ownership belong in core/platform/.
core/config/ is a frontend-facing settings facade and split/merge persistence adapter. Do not treat it as a bounded context.
core/shared/ is only for highly stable shared kernel concepts. Do not move context-local IDs or business rules there unless they are genuinely cross-context.
cmd/skillflow/ remains the Wails desktop shell, transport adapter layer, process host, and composition root.
wails.json must stay co-located with frontend/ inside cmd/skillflow/.
The //go:embed all:frontend/dist directive in main.go works because both are in cmd/skillflow/.
go test ./core/... is run from the module root.
Import paths use the full module path: github.com/shinerio/skillflow/core/....
cmd/skillflow/*.go files must remain flat. Wails bindings require a single package main directory, so do not create subdirectories under cmd/skillflow/.
Use file-name prefixes inside cmd/skillflow/ as the organization convention:
- app.go, app_*.go for Wails-facing transport methods
- events.go for shell event types and emitters
- adapters.go, providers.go for shell-side wiring
- process_*.go, tray_*.go, window_*.go, single_instance_*.go for shell/runtime concerns
When a concern grows large enough to warrant its own package, extract it to core/ rather than creating a subdirectory inside cmd/skillflow/.

Read the full file on GitHub · 370 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.

2d ago First seen · 370 lines · 4,744 tokens per session scan A a2d7adc57341

Subscribe to this mod's changes

SkillFlow AGENTS.md is an instructions file published in the GitHub repository shinerio/SkillFlow (24 stars, last pushed 2d ago), licensed MIT. It adds 4,744 tokens to every session, about $0.0237 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.

Data and AI LLM Memory and context Writing and docs ai desktop-app prompt skill skills

SkillFlow AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Directory Organization Rule - MANDATORY

What this file has done since we first saw it

Other instructions, from other repositories

rolecraft AGENTS.md

skills AGENTS.md

claude-skills CLAUDE.md

claude-skills AGENTS.md

Loop AGENTS.md

SonarCloud-Skill-Agent-Guidance