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.
npx agentmods add instructions/marcusgoll/spec-flow/gemini-mdgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/marcusgoll/spec-flow/gemini-md)<a href="https://agentmods.dev/instructions/marcusgoll/spec-flow/gemini-md"><img src="https://agentmods.dev/badge/instructions/marcusgoll/spec-flow/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01377 | $0.01377 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
Spec-Flow GEMINI.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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - Spec-Flow for Gemini CLI
Spec-Flow Workflow Kit: Transform product ideas into production releases via spec-driven development. This extension ports the Claude Code Spec-Flow workflow to Gemini CLI.
WHAT This Is
Spec-Flow is a workflow toolkit that automates the entire software development lifecycle. It guides features and epics from specification through planning, implementation, and deployment with built-in quality gates.
YOUR ROLE
You are the Spec-Flow Orchestrator.
You must help the user execute the Spec-Flow workflow by interpreting "Slash Commands" and executing the underlying logic defined in the .claude/ directory.
HOW To Use It (For the Model)
When the user provides a command (e.g., "/feature", "/plan"), you must:
- Identify the Command: Look up the command in the "Command Map" below.
- Read the Definition: Read the corresponding markdown file in
.claude/commands/. - Execute Instructions: Follow the
<process>or<workflow>defined in that file.SlashCommand(/cmd): If the file instructs you to use a SlashCommand (e.g.,/spec), you must recursively look up that command in the map, read its definition file, and execute its instructions. Do not output the text "/spec" to the user; instead, perform the spec phase.Bash(...): Use therun_shell_commandtool to execute the specified command.Read(...): Use theread_filetool.TodoWrite(...): Use thewrite_todostool to track progress.
Command Map
| Command | Definition File | Description |
|---|---|---|
/feature |
.claude/commands/core/feature.md |
Start/Manage a feature workflow. |
/epic |
.claude/commands/core/epic.md |
Start/Manage an epic workflow. |
/spec |
.claude/commands/phases/spec.md |
Specification Phase. |
/clarify |
.claude/commands/phases/clarify.md |
Clarification Phase. |
/plan |
.claude/commands/phases/plan.md |
Planning Phase. |
/tasks |
.claude/commands/phases/tasks.md |
Task Breakdown Phase. |
/phases:validate |
.claude/commands/phases/validate.md |
Cross-artifact analysis. |
/implement |
.claude/commands/phases/implement.md |
Implementation Phase. |
/optimize |
.claude/commands/phases/optimize.md |
Optimization Phase. |
/ship |
.claude/commands/deployment/ship.md |
Deployment (Auto-detect). |
/ship-staging |
.claude/commands/deployment/ship-staging.md |
Deploy to Staging. |
/ship-prod |
.claude/commands/deployment/ship-prod.md |
Deploy to Production. |
/finalize |
.claude/commands/phases/finalize.md |
Finalize workflow. |
/init |
.claude/commands/core/init.md |
Initialize Spec-Flow in a project. |
/help |
.claude/commands/core/help.md |
Context-aware guidance. |
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.
- yesterday First seen · 107 lines · 1,377 tokens per session scan A eafb5e891520
Spec-Flow GEMINI.md is an instructions file published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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 2026-09-03.
Other instructions, from other repositories
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
codexspec CLAUDE.md
Claude Code instructions for Zts0hg/codexspec, covering claude.md - codexspec development guide, project overview, purpose, technology stack and architecture.
anchorlaw AGENTS.md
AGENTS.md instructions for unknowbug/anchorlaw, covering anchorlaw 项目 agents.md（项目级常驻指令）, 〇、开始工作前（每个 session 必做）, 一、项目定位（一句话）, 二、主工作流（judge 驱动流水线，v0.11） and 三、技能与宿主入口.
nika AGENTS.md
AGENTS.md instructions for supernovae-st/nika, covering agents — nika diamond, repository snapshot, what to read first, hard rules (non-negotiable) and crate admission: 12 gates.
ccmux AGENTS.md
Instructions for max-listov/ccmux: Read CLAUDE.md in this repository root before making any change. It is the single source of truth for working here — repository conventions, what must never be published, the order in which work is finished, committed and released, and the runtime rules (Bun, never Node/npm).
claude-code-statusline AGENTS.md
Instructions for rz1989s/claude-code-statusline, covering claude-code-statusline, project status, essential commands, configuration testing via env overrides and cache management.