spec-kit-copilot AGENTS.md

Repository-specific guidance for maintaining the Spec Kit Copilot integration hub, a project that connects GitHub Copilot with Spec Kit commands and related extensions.

In plain words
What is it for?
Use it when adding, removing, or regenerating skills and other Copilot integration files in this repository.
Why use it?
It preserves key project decisions and explains which integration belongs where, reducing the chance of breaking the repository's intended structure.

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/github/spec-kit-copilot/agents-md
Clone the repo
git clone --depth 1 https://github.com/github/spec-kit-copilot

Made for: Codex, OpenCode.

Per session 2,177 This file is loaded in full into every session.
When invoked 2,177 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 $0.02177 $0.02177
Opus 5 $0.01089 $0.01089
Sonnet 5 $0.00435 $0.00435
Haiku 4.5 $0.00218 $0.00218

Measured yesterday against content hash b3e0650276df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-kit-copilot 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 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.

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 — Maintainer guidance for Spec Kit Copilot integrations

This file captures the design decisions behind these integrations so they are not accidentally reverted when revving or regenerating it. Read this before adding, removing, or regenerating skills.

What this repository is

The Copilot integration hub for Spec Kit. It can contain independently versioned Copilot CLI/App plugins, skills, extensions, canvases, hooks, and workflow surfaces. Do not assume every integration belongs in the core skills plugin.

Core skills plugin

A GitHub Copilot CLI plugin (plugin.json + skills/<name>/SKILL.md) that exposes the Spec Kit specify CLI to the Copilot agent. Each skill documents a specify command group and tells the agent when and how to shell out to specify. The plugin does not dispatch prompts to another agent — Copilot itself runs the CLI.

Core decisions (do not silently undo)

  1. The integration is always Copilot in skills mode — do NOT expose specify integration. This is the Copilot plugin, so the agent is already Copilot. Managing or switching integrations (claude, gemini, etc.) is meaningless here. There is intentionally no speckit-integration skill. Do not re-add it when regenerating the skill set.

    • speckit-init always scaffolds Copilot in skills mode: --integration copilot --integration-options="--skills". Skills mode makes spec-kit commands (and later-added extensions) install as Copilot Agent Skills (.github/skills/speckit-<cmd>/SKILL.md) instead of .agent.md files, which is what Copilot CLI discovers as SKILL.md. Do not drop --integration-options="--skills".
    • Skills must not tell the user to pick or switch a different agent.
  2. Expose the rest of the specify surface as skills, including nested catalog subcommands and workflow step:

    • speckit-cli-setup → detect/install the specify CLI (bootstrap; prerequisite for all others)
    • speckit-initspecify init (Copilot only)
    • speckit-checkspecify check, specify version
    • speckit-extensionspecify extension … (+ catalog)
    • speckit-presetspecify preset … (+ catalog)
    • speckit-bundlespecify bundle … (+ catalog)
    • speckit-workflowspecify workflow … (+ catalog)
    • speckit-workflow-stepspecify workflow step … (+ catalog)
    • speckit-selfspecify self …

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. yesterday First seen · 135 lines · 2,177 tokens per session scan A b3e0650276df

Subscribe to this mod's changes

spec-kit-copilot AGENTS.md is an instructions file published in the GitHub repository github/spec-kit-copilot (11 stars, last pushed 5d ago), licensed MIT. It adds 2,177 tokens to every session, about $0.0109 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.

Related

Other instructions, from other repositories

copilot-brag-sheet AGENTS.md

Instructions for microsoft/copilot-brag-sheet, covering agents.md, 1. project overview, 2. architecture map, 3. build / test / lint commands and run a single test file.

microsoft/copilot-brag-sheet · 9,573 tokens

spec-kitty AGENTS.md

Instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.

Priivacy-ai/spec-kitty · 9,409 tokens

squad copilot-instructions.md

Instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.

bradygaster/squad · 1,349 tokens

vscode-unify-chat-provider AGENTS.md

Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…

smallmain/vscode-unify-chat-provider · 271 tokens

apex-accelerator agent-skills.instructions.md

Guidelines for creating high-quality Agent Skills for GitHub Copilot.

jonathan-vella/apex-accelerator · 1,962 tokens

apex-accelerator code-quality.instructions.md

Code quality guidelines: commenting best practices (WHY not WHAT) and review priorities with security checks.

jonathan-vella/apex-accelerator · 943 tokens