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/github/spec-kit-copilot/agents-mdgit clone --depth 1 https://github.com/github/spec-kit-copilotWhat 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 | $0.02177 | $0.02177 |
| Opus 5 | $0.01089 | $0.01089 |
| Sonnet 5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00218 | $0.00218 |
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.
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)
-
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 nospeckit-integrationskill. Do not re-add it when regenerating the skill set.speckit-initalways 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.mdfiles, which is what Copilot CLI discovers asSKILL.md. Do not drop--integration-options="--skills".- Skills must not tell the user to pick or switch a different agent.
-
Expose the rest of the
specifysurface as skills, including nestedcatalogsubcommands andworkflow step:speckit-cli-setup→ detect/install thespecifyCLI (bootstrap; prerequisite for all others)speckit-init→specify init(Copilot only)speckit-check→specify check,specify versionspeckit-extension→specify extension …(+catalog)speckit-preset→specify preset …(+catalog)speckit-bundle→specify bundle …(+catalog)speckit-workflow→specify workflow …(+catalog)speckit-workflow-step→specify workflow step …(+catalog)speckit-self→specify self …
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 · 135 lines · 2,177 tokens per session scan A b3e0650276df
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.
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.
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.
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.
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…
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
apex-accelerator code-quality.instructions.md
Code quality guidelines: commenting best practices (WHY not WHAT) and review priorities with security checks.