feature-requests

This document covers how podkit manages feature requests across GitHub Discussions, documentation, and the backlog. Follow these instructions when creating, updating, or closing feature requests.

Agent

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 agents/jvgomg/podkit/feature-requests
Clone the repo
git clone --depth 1 https://github.com/jvgomg/podkit
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 2,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.02991
Opus 5 $0.00000 $0.01496
Sonnet 5 $0.00000 $0.00598
Haiku 4.5 $0.00000 $0.00299

Measured yesterday against content hash 6ad3d41aa8e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-requests scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
agents/feature-requests.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Requests: Agent Guide

This document covers how podkit manages feature requests across GitHub Discussions, documentation, and the backlog. Follow these instructions when creating, updating, or closing feature requests.

Overview

Feature requests live in three places that must stay in sync:

Location Purpose Audience
GitHub Discussions (Ideas category) Public voting, comments, and status updates Users and contributors
Documentation (docs/project/roadmap.md, callouts in other docs) Communicates what's planned and links to discussions Users reading the docs
Backlog tasks (Backlog.md) Internal tracking, implementation plans, acceptance criteria Developers

The GitHub Discussion is the source of truth for public-facing feature status. The roadmap doc page and the pinned Roadmap discussion (#17) are derived views. The backlog task tracks implementation details.

GitHub Discussions

Repository setup

  • Discussions are enabled on jvgomg/podkit
  • Ideas category is used for feature requests (supports upvoting)
  • Announcements category contains the pinned Roadmap discussion (#17)

Creating a new feature discussion

Use the GitHub GraphQL API via the gh CLI. Shell escaping of the body is tricky — use a Python helper:

import subprocess, json

REPO_ID = "R_kgDORjcW4Q"
IDEAS_CAT = "DIC_kwDORjcW4c4C4Hnu"  # Ideas category
ANNOUNCE_CAT = "DIC_kwDORjcW4c4C4Hnr"  # Announcements category
QUERY = "mutation($input: CreateDiscussionInput!) { createDiscussion(input: $input) { discussion { number url } } }"

def create_discussion(title, body, category_id=IDEAS_CAT):
    payload = json.dumps({
        "query": QUERY,
        "variables": {"input": {
            "repositoryId": REPO_ID,
            "categoryId": category_id,
            "title": title,
            "body": body
        }}
    })
    result = subprocess.run(
        ["gh", "api", "graphql", "--input", "-", "--jq",
         '.data.createDiscussion.discussion | "\\(.number) \\(.url)"'],
        input=payload, capture_output=True, text=True
    )
    return result.stdout.strip()  # "42 https://github.com/jvgomg/podkit/discussions/42"

Read the full file on GitHub · 309 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. yesterday First seen · 309 lines · 0 tokens per session scan A 6ad3d41aa8e1

Subscribe to this mod's changes

feature-requests is an agent published in the GitHub repository jvgomg/podkit (39 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,991 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.