feature-doc

A documentation workflow that creates a feature specification, an implementation guide, and test cases for one feature and one actor. It also updates the feature documentation index.

In plain words
What is it for?
Use it to prepare a feature for later implementation and to document expected behavior, technical guidance, and tests in the project's docs.
Why use it?
It exposes missing details such as users, triggers, prerequisites, data sources, and edge cases before code is written.

Command for Claude Code

Part of the agent-harness plugin — 35 skills, 9 commands, 12 agents 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/ghosteken/agent-harness/feature-doc
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code.

Or install agent-harness, the plugin that ships this one along with the rest of its 35 skills, 9 commands, 12 agents.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 163 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 $0.00023 $0.00163
Opus 5 $0.00012 $0.00081
Sonnet 5 $0.00005 $0.00033
Haiku 4.5 $0.00002 $0.00016

Measured 2d ago against content hash 71ed6d3c652e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-doc 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.

.claude/commands/feature-doc.md · 12 lines

What it actually says

Invoke the agent-harness:feature-doc skill.

Identify the feature to document, then locate and read the project's own technical/product docs before asking anything else. Interview the user to resolve every material unknown the docs don't already answer — actors, triggers, preconditions, data sources, edge cases — never assume or default anything feature-specific.

Produce three cross-referenced artifacts under docs/features/<feature-slug>/<actor-slug>/: feature-spec.md, implementation-guide.md, and test-cases.md, and update the index at docs/features/README.md.

State clearly that this output is a planning artifact — implementing the feature is a separate, later step.

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 · 12 lines · 23 tokens per session scan A 71ed6d3c652e

Subscribe to this mod's changes

feature-doc is a command published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 163 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 2026-08-31.