gitflow-cli CLAUDE.md

Repository instructions for working on gf, a Rust 2024 workspace template and Gitflow command-line project. They define required coding practices, workflow limits, and files that must remain unchanged.

In plain words
What is it for?
Use them when editing the gf repository, running its development workflow, preserving placeholders, managing agent state, or deciding whether a requested operation needs permission.
Why use it?
They prevent an agent from making unauthorized project, template, dependency, or release changes while maintaining the code.

Instructions file

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/byx-darwin/gitflow-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/byx-darwin/gitflow-cli
Per session 4,417 This file is loaded in full into every session.
When invoked 4,417 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 $0.04417 $0.04417
Opus 5 $0.02209 $0.02209
Sonnet 5 $0.00883 $0.00883
Haiku 4.5 $0.00442 $0.00442

Measured yesterday against content hash 809dc2fe81de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gitflow-cli CLAUDE.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 yesterday.

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.

CLAUDE.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gf Agent Guide

This repository is a reusable Rust 2024 workspace template. These rules are mandatory when working in this template.

Non-negotiables

  • Never enter plan mode automatically.
  • Preserve template placeholders such as gf unless the user explicitly asks to instantiate the template.
  • Do not replace template variables with concrete project names during maintenance.
  • Use CLAUDE.md as the single project-level agent instruction file.
  • Use Ruflo for agent workflow/orchestration. Do not maintain project-local .claude/skills unless explicitly requested.
  • Keep Ruflo or Claude-flow runtime state out of git; persist reusable guidance in CLAUDE.md, docs/, or specs/.
  • Do not commit, push, merge, release, deploy, install dependencies, or change ticket state without explicit user permission.
  • Never run cargo clean; ask first if it is truly required.
  • Never write TODO, todo!(), temporary stubs, or incomplete code. If blocked, stop, reassess, and implement the complete solution.
  • Remove dead code instead of suppressing it. Do not add deprecation layers unless explicitly requested.
  • Never expose secrets in commands, logs, URLs, comments, errors, or tool arguments.
  • 禁止修改以下配置文件(除非用户明确要求):deny.toml 中的 allow/deny/wildcards 等策略配置、.pre-commit-config.yaml 中的 hook 类型和阶段配置、rust-toolchain.toml 中的工具链版本。这些配置影响 CI/CD 流程,变更需用户确认。
  • 严格执行 gf-workflow 流程:当使用 /gf-workflow 时,必须按照四阶段完整流程执行:
    • 阶段 1:需求澄清(从 open issues 读取,支持完整模式和快速模式)
    • 阶段 2:计划制定(生成完整计划闭环)
    • 阶段 3:执行(调用 subagent-driven-development)
    • 阶段 4:交付后检查(流水线分析、Issue 分类、代码审查)
    • 不可跳过: TDD 循环和代码审查在所有模式下均为必须步骤

Completion Discipline

  • Do Not Stop Early: If the user's requested outcome is not fully complete, do not stop at a draft, partial pass, or "good enough" result. Continue reviewing and improving until the request is genuinely handled or a concrete blocker requires user input.
  • Polish Bar: Before declaring work complete, ask whether the result is fully polished, concrete, correct, complete, and elegant. If there is doubt, review the work again and update it.
  • Honest Status: Do not claim a task is finished when it is only a first pass, scaffold, or partial draft. State the remaining gaps and keep working unless the user explicitly asks to pause.

Read the full file on GitHub · 314 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. yesterday First seen · 314 lines · 4,417 tokens per session scan A 809dc2fe81de

Subscribe to this mod's changes

gitflow-cli CLAUDE.md is an instructions file published in the GitHub repository byx-darwin/gitflow-cli (2 stars, last pushed yesterday), licensed MIT. It adds 4,417 tokens to every session, about $0.0221 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.

Related

Other instructions, from other repositories

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

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

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

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

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

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