feature-docs

A documentation workflow for adding feature pages and screenshots to the AgentOp project. It requires capturing the running app in the requested state and reading the source code before writing the description.

In plain words
What is it for?
Use it when documenting a new feature, taking its screenshot, or updating the feature list in the README. It saves the screenshot in the project’s documentation image folder.
Why use it?
It keeps feature documentation tied to the actual interface and implementation. The required order helps prevent descriptions based only on assumptions.

Skill for Claude CodeCodex

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 skills/macromania/agentop/feature-docs
Any agent
npx skills add macromania/agentop --skill feature-docs
Clone the repo
git clone --depth 1 https://github.com/macromania/agentop

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,060 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 $0.00055 $0.01060
Opus 5 $0.00028 $0.00530
Sonnet 5 $0.00011 $0.00212
Haiku 4.5 $0.00006 $0.00106

Measured 2d ago against content hash e6c07ffe565d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-docs 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/skills/feature-docs/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Documentation

Create feature documentation pages with screenshots for the AgentOp project.

When to Use This Skill

  • Documenting a new feature with a screenshot
  • Taking a screenshot of the running Electron app
  • Writing a feature description page
  • Adding a feature entry to the README

CRITICAL: Required Process

You MUST follow these steps in exact order. Do NOT skip or reorder any step.

The user will get the app into the desired visual state and tell you the feature name. Only then do you proceed.

Step 1 — Capture Screenshot

The user has the app running and showing the feature. Capture the app window:

# Interactive window capture — user clicks the AgentOp window
screencapture -w docs/images/{feature-name}.png
  • Use kebab-case for the filename matching the feature name
  • Save to docs/images/
  • The -w flag lets the user click the target window
  • Wait for confirmation that the screenshot was saved successfully

Step 2 — Read Code to Understand the Feature

This step is NOT optional. You MUST read the actual source code before writing any description.

Search the codebase to find the components, hooks, IPC handlers, state atoms, and backend logic related to the feature. Read them thoroughly.

Where to look:

Layer Path What to look for
UI Components apps/electron/src/renderer/components/ React components rendering the feature
Hooks apps/electron/src/renderer/hooks/ Data fetching, state management for the feature
State apps/electron/src/renderer/state/ Jotai atoms related to the feature
IPC Handlers apps/electron/src/main/ipc/ Backend handlers the feature calls
Agent Logic apps/electron/src/main/agent/ Orchestrator, planner, session logic
Shared Logic packages/shared/src/ Database schema, business logic
Core Types packages/core/src/types.ts Type definitions for the feature's domain

Read the full file on GitHub · 112 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 · 112 lines · 55 tokens per session scan A e6c07ffe565d

Subscribe to this mod's changes

feature-docs is a skill published in the GitHub repository macromania/agentop (10 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,060 once invoked, about $0.0003 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.