feature-request

A guided workflow for drafting a feature-request issue on GitHub, the service used to track changes and improvements in software. It targets the lean4-skills project.

In plain words
What is it for?
Use it to collect the needed details and prepare a feature request for lean4-skills. It asks for confirmation before drafting or submitting anything.
Why use it?
It helps turn a loosely described problem into a complete issue with consent, context, alternatives, and clear acceptance criteria.

Command

Part of the lean4-contribute plugin — 3 commands shipped together

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 commands/cameronfreer/lean4-skills/feature-request
Clone the repo
git clone --depth 1 https://github.com/cameronfreer/lean4-skills

Or install lean4-contribute, the plugin that ships this one along with the rest of its 3 commands.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00013 $0.00836
Opus 5 $0.00006 $0.00418
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00001 $0.00084

Measured 3d ago against content hash 0ef61c86dc61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-request 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 3d 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.

plugins/lean4-contribute/commands/feature-request.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Request

Draft and submit a feature request as a GitHub issue on cameronfreer/lean4-skills.

Precondition

Invoke this command only if the user explicitly ran it or explicitly agreed to draft a feature request. If invoked without prior opt-in, ask:

This looks like a plugin workflow gap. Want me to draft a feature request?

If the user explicitly ran /lean4-contribute:feature-request, treat that as opt-in. Do not proceed unless the user confirms. Do not gather structured questions or build an issue body until consent is given.

Gathering Context

Collect the following from the user and the current session. Ask for anything you cannot infer:

  1. Problem / pain point — What is frustrating, slow, or missing?
  2. Current workaround — How do you handle this today? (or "none")
  3. Desired behavior — What should the plugin do instead?
  4. Why this belongs in the plugin — Why is this a plugin concern rather than a user-side script or external tool?
  5. Acceptance criteria — Concrete conditions that would mark this done
  6. Alternatives considered — Other approaches you thought of and why they fall short
  7. Urgency / frequency — How often do you hit this? Blocking, frequent annoyance, nice-to-have?

Drafting the Issue

Compose the issue using this template:

Title: [Feature] <short description>
Labels: enhancement

## Problem / Pain Point
<problem description>

## Current Workaround
<workaround or "none">

## Desired Behavior
<what the plugin should do>

## Why This Belongs in the Plugin
<justification>

## Acceptance Criteria
- [ ] <criterion 1>
- [ ] <criterion 2>
- ...

## Alternatives Considered
<other approaches and trade-offs>

## Urgency / Frequency
<how often, how blocking>

---
*Drafted via [lean4-contribute](https://github.com/cameronfreer/lean4-skills)*

Showing the Draft

Display the complete issue draft to the user — title, labels, and full body. Ask:

Here is the feature request I will submit. Review it carefully.

By submitting, you agree that this content may be edited, rearranged, or incorporated into lean4-skills in any form under its MIT license.

Submit this issue? (yes / edit / cancel)

Read the full file on GitHub · 105 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. 3d ago First seen · 105 lines · 13 tokens per session scan A 0ef61c86dc61

Subscribe to this mod's changes

feature-request is a command published in the GitHub repository cameronfreer/lean4-skills (418 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 836 once invoked, about $0.0001 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.