structured-autonomy-implement Skill (awesome-copilot): What It Does and How to Install It

Makes the assistant carry out an implementation plan exactly as written and stop at each STOP instruction.

Installs: 8.8K; on skills.sh
Stars: 40.7K; on GitHub
Updated: Oct 2026; last repo commit

This skill tells the assistant to follow an implementation plan exactly. It picks up at the next unchecked step, writes only what the plan specifies, ticks off items in the plan file, runs the plan's build or test commands, and stops at the STOP instruction.

It needs the plan passed in. Without one it replies "Implementation plan is required." It bundles no scripts and the SKILL.md names no API key. Its plan usually comes from structured-autonomy-generate.

Good for

Developers who hand an implementation plan to a cheaper, faster model
Teams that want one reviewed commit per plan step
Anyone using the structured-autonomy plan, generate, implement flow

Install structured-autonomy-implement

Claude Code

Copy this prompt.

Install the structured-autonomy-implement skill in Claude Code. Run this command:

npx skills add https://github.com/github/awesome-copilot --skill structured-autonomy-plan --skill structured-autonomy-generate --skill structured-autonomy-implement

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

Install all three skills together. structured-autonomy-plan writes plans/{feature-name}/plan.md, generate turns it into implementation.md, and implement carries it out. The Copilot plugin route installs the structured-autonomy plugin, which lists the same 3 skills and no agents, hooks or MCP servers. The skill edits project files and runs build commands, so there is no Claude app upload route.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

Structured Autonomy Implementation Prompt

Key facts

Author: Awesome Copilot Community (listed as the plugin author)
License: MIT
Installs on skills.sh: 8,774 (Nov 2, 2026)
GitHub stars: 40,666 for the whole github/awesome-copilot repo (Nov 2, 2026)
Last repo commit: Oct 30, 2026
Audits on skills.sh: Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass
What it includes: 1 file including SKILL.md
Part of: Copilot plugin structured-autonomy: 3 skills (plan, generate, implement), described as "Premium planning, thrifty implementation"

What it includes

Without a plan as input it replies "Implementation plan is required."
The agent must be given the implementation plan document.
Require the plan
Picks up at the next unchecked step and skips nothing.
It implements only what the plan specifies and writes no code outside it.
Write · Follow the plan exactly
Ticks each item in the plan document as the step is completed.
It edits the plan file itself using standard markdown checkboxes.
Write · Check off items inline
Runs the build or test commands the plan specifies.
The commands come from the plan, not from the skill.
Runs code · Verify with the plan's commands
Halts at the plan's STOP instruction and hands control back to you.
You then test, stage and commit before the next step.
Stop at STOP

From the official docs

Permissions

Medium risk

It edits your code and runs the build or test commands written in the plan. Read the plan first and check the diff at each stop.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It runs commands that the plan contains
The skill runs the build or test commands specified in the plan. Read the plan, especially its commands, before you start. github.com
It edits your code and the plan file
It changes only what the plan specifies, but you still need to review each step. The plan has a STOP after each step for exactly that. github.com

Technical details

Turning on read-only	No read-only mode. The skill exists to implement the plan.
Scopes	Edits the files the plan names Edits the plan document to tick off items Runs the build or test commands written in the plan

Questions

What does structured-autonomy-implement do?

It makes the assistant carry out an implementation plan step by step, exactly as written. It writes no code the plan does not specify, ticks off items in the plan file, runs the plan's build or test commands, and stops where the plan says STOP.

Where does the plan come from?

You pass it in. If you do not, the skill replies "Implementation plan is required." The sibling skill structured-autonomy-generate writes plans/{feature-name}/implementation.md (its SKILL.md), and structured-autonomy-plan writes the plan.md that generate reads.

How do I install it?

Use the install box above. In Copilot CLI the structured-autonomy plugin adds all three skills. With the skills CLI the command names all three, so the plan and generate steps are available too.

Does it commit my code?

The SKILL.md does not say to commit. It says to stop at the plan's STOP instruction and return control to you. The generated plan template tells you to test, stage and commit at each stop.

Is it safe?

It bundles no scripts, but it edits your code and runs whatever build or test commands the plan lists. Review the plan before you start, and check the diff at each STOP.

Does it work in Claude Code?

The SKILL.md names no client. It is a short prompt: a role, a workflow of six bullets and the plan input. The install box has Claude Code folder and skills CLI routes.

Information

updated Nov 2, 2026

Repository: github/awesome-copilot
Folder: skills/structured-autonomy-implement

github/awesome-copilot skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

structured-autonomy-implement SKILL.md · github.com
structured-autonomy plugin.json · github.com
structured-autonomy plugin README · github.com
awesome-copilot README · github.com
SKILL.md · github.com