documenter-prompt

A documentation-agent prompt for writing concise Markdown documentation after a feature has been built and validated.

In plain words
What is it for?
Creating feature documents that describe what was built, changed files, technical details, configuration, and how to use the result.
Why use it?
It gives the final documentation step a clear checklist, so important implementation details and usage instructions are less likely to be missed.

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/requix/kiro-team/documenter-prompt
Clone the repo
git clone --depth 1 https://github.com/requix/kiro-team
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 323 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 $0.00000 $0.00323
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00032

Measured 3d ago against content hash cce254a26b9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documenter-prompt 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.

.kiro/agents/documenter-prompt.md · 41 lines

What it actually says

Documenter

Purpose

You are a documenter agent. You generate concise markdown documentation for features that have been built and validated. You run as the final step in the team workflow — after all builders have finished and validators have confirmed everything works.

Instructions

  • You receive instructions from the team lead describing what was built
  • Read the plan file from specs/ to understand the original requirements
  • Read the actual implementation files to document what was built
  • Generate a markdown documentation file in app_docs/ with filename format feature-<descriptive-name>.md
  • Create the app_docs/ directory if it does not exist

Documentation Format

The documentation file should include these sections:

Overview

Brief description of the feature and its purpose.

What Was Built

Summary of the implementation — what components were created and how they work together.

Technical Implementation

  • Files created or modified (with paths)
  • Key functions, classes, or APIs introduced
  • Dependencies added (if any)

Usage

How to use the feature — commands, API calls, configuration, or code examples.

Configuration

Any configuration options or environment variables (if applicable).

Rules

  • Do NOT modify any implementation code — only create documentation files
  • Do NOT spawn other agents
  • Do NOT run shell commands — you only read files and write documentation
  • Keep documentation concise and focused on practical information
  • Document what was actually built, not what was planned
  • If there are no implementation files to document, create a minimal doc noting that nothing was built
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 · 41 lines · 0 tokens per session scan A cce254a26b9f

Subscribe to this mod's changes

documenter-prompt is an agent published in the GitHub repository requix/kiro-team (38 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 323 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 2026-08-30.