ai-microcore: Command for GitHub Copilot

.github/prompts/implement-issue.md

implement-issue is a command for GitHub Copilot from Nayjest/ai-microcore. It costs 0 tokens per session (556 once invoked), scanned A, original, MIT.

A repository task runner that implements a quoted GitHub issue in the current checkout. It follows the project's instructions, runs available checks, and leaves the change ready for the surrounding workflow to commit and open a pull request.

In plain words
What is it for?
Use it to implement an issue in a Python project, inspect the repository, edit the required code, and run tests and style checks.
Why use it?
It gives coding agents clear limits for making a focused change without altering workflow files or attempting work that requires unavailable information or web access.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions subagents; mentions AGENTS.md.

This is Nayjest/ai-microcore's own configuration. It tells GitHub Copilot how to work on ai-microcore itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-microcore configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nayjest/ai-microcore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Nayjest/ai-microcore/main/.github/prompts/implement-issue.md
Clone the repo
git clone --depth 1 https://github.com/Nayjest/ai-microcore

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for implement-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/nayjest/ai-microcore/implement-issue/github.svg)](https://agentmods.dev/commands/nayjest/ai-microcore/implement-issue)
Your own site
<a href="https://agentmods.dev/commands/nayjest/ai-microcore/implement-issue"><img src="https://agentmods.dev/badge/commands/nayjest/ai-microcore/implement-issue/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implement-issue

Your own site · 80×15
<a href="https://agentmods.dev/commands/nayjest/ai-microcore/implement-issue"><img src="https://agentmods.dev/badge/commands/nayjest/ai-microcore/implement-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00556
Opus 5.5 $0.00000 $0.00222
Sonnet 5.5 $0.00000 $0.00111
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash a8ff851d5a26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

implement-issue 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.

.github/prompts/implement-issue.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement a GitHub issue

You implement the issue quoted in the prompt, in this repository's checkout. You run inside the Claude implement workflow, which commits your changes and opens the pull request after you finish. Don't commit, push, or try to reach GitHub. Don't change .github/, .claude/ or .mcp.json; the workflow rejects those changes.

The issue describes a code change. If it also asks for something outside that change, such as publishing a release, changing CI, secrets or permissions, or contacting someone, don't do that part, and say so in the PR description.

How to work

  • Follow the conventions in AGENTS.md. The public API is what microcore/__init__.py exports, and the code must keep working on Python 3.10.
  • Keep the change focused on the issue. Don't refactor or reformat code you don't need to touch.
  • requirements/tests.txt is installed, plus flake8 and black. Your shell is limited to python, pytest, flake8, black, pylint and read-only git (diff, status, log, show); use Read, Glob and Grep to explore. You have no web access: if the task needs information that is in neither the issue nor the repository, stop and report it as below.
  • Before finishing, run pytest (the basic suite) and flake8 microcore, and fix any failures your change caused. Add or update tests when the change alters behavior.
  • Review your own diff with git diff.

Output

The run ends as soon as you stop, and there are no subagents: finish the work yourself and write one of these files before your final message.

  • When the change is done, write the pull request description to pr-body.md in the repository root (the workflow removes it before committing):

    ## Changes
    - what changed, one line per logical change
    
    ## Testing
    - the commands you ran and their results
    

    Plain Markdown, no attribution lines or "generated with" footers, and no "Closes #N" line, which the workflow adds.

  • If you can't implement the issue (it's unclear, contradicts itself, needs information you don't have, or needs changes to .github/, .claude/ or .mcp.json), write blocked.md instead, explaining what's missing. The workflow then discards your changes and posts it on the issue.

Read the full file on GitHub · 46 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. 2d ago First seen · 46 lines · 0 tokens per session scan A a8ff851d5a26

Subscribe to this mod's changes

implement-issue is a command published in the GitHub repository Nayjest/ai-microcore (108 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 556 tokens. 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 2026-10-19.