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/cskishan/ame-skill/agents-mdgit clone --depth 1 https://github.com/CSKishan/ame-skillWhat 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 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
ame-skill 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AME + EMA — Agent Pipeline Documentation
What Is This?
Two VS Code Copilot Chat skills that work as a pipeline:
/ame → single compiled interview → .ame/spec.md
/ema → layer analysis → .ame/plan.md → chunked execution
/ame (Ask Me Exhaustively) closes the requirement gap before any code is written. It compiles all applicable interview questions into one message across five quality dimensions — tech stack, architecture, security, quality, and edge cases — and produces a structured spec file from your answers. Total exchanges: 2–3.
/ema (Enclose My Analysis) reads that spec, identifies which architectural layers the project spans, and generates a dependency-ordered, chunked implementation plan. It offers chunk-by-chunk execution (with per-chunk confirmation) or a "run all" mode for one-shot execution.
Requirements
- VS Code with GitHub Copilot Chat
- Agent mode — both skills write files to the workspace; Ask mode is not sufficient
- Optional: context7 MCP server for live library documentation during the interview
Install
Manual
- Clone or download this repository
- Copy
skills/ame/SKILL.mdto your agents skills folder:- Windows:
%USERPROFILE%\.agents\skills\ame\SKILL.md - macOS/Linux:
~/.agents/skills/ame/SKILL.md
- Windows:
- Copy
skills/ema/SKILL.mdto:- Windows:
%USERPROFILE%\.agents\skills\ema\SKILL.md - macOS/Linux:
~/.agents/skills/ema/SKILL.md
- Windows:
- Restart VS Code
Via skills CLI
npx skills add github:CSKishan/ame-skill
Usage
Full workflow
1. Open VS Code Copilot Chat in Agent mode
2. Describe what you want to build, then invoke:
/ame I want to build a REST API for managing IoT device telemetry
3. AME detects scope, compiles all applicable dimension questions into
one message. Answer everything at once — free-form or labelled.
4. AME processes your answers, writes .ame/spec.md, and presents a
plain-English summary. Confirm it or correct anything in one reply.
5. When done, invoke:
/ema
6. EMA reads .ame/spec.md, generates .ame/plan.md,
shows a chunk summary, and waits for your confirmation to execute.
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 · 179 lines · 1,499 tokens per session scan A 400d256202b6
ame-skill AGENTS.md is an instructions file published in the GitHub repository CSKishan/ame-skill (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,499 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
packmind packmind-frontend-error-management.instructions.md
Instructions for PackmindHub/packmind: A global error boundary is already configured at the root level (in root.tsx) that automatically catches all page crashes, 404s, and loader failures. This standard defines when and how to use explicit... .
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
apex-accelerator no-interactive-shell.instructions.md
Prevents interactive shell prompts and long-output terminal replays from being injected into chat. Forbids -i flags on mv/rm/cp, read -p, and confirm prompts (incl. inside bash -c '...'). Pipe long output to files. Scoped to chat-context-loaded files; skill references/ and templates/ are exempt because they hold…
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.