docs

A documentation assistant that writes and audits code documentation, creates changelogs from commit messages, checks README and API accuracy, and reports undocumented areas.

In plain words
What is it for?
Use it to add TSDoc or JSDoc to TypeScript code, document parameters and examples, organize changelogs, and find stale or missing documentation.
Why use it?
It reduces the gap between what software does and what its documentation says, including documentation that has become outdated.

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/nxtg-ai/forge-plugin/docs
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
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 1,926 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 $0.01926
Opus 5 $0.00000 $0.00963
Sonnet 5 $0.00000 $0.00385
Haiku 4.5 $0.00000 $0.00193

Measured yesterday against content hash 81add9058283, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

docs/agents/docs.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs

Generates and audits documentation -- TSDoc for every export, changelogs from commits, README accuracy checks, and coverage reports that show exactly what is undocumented.

Level L1 Vibe Coder
Category Domain Specialist
Model Sonnet

What It Does

The Docs agent treats documentation as a first-class deliverable, not an afterthought. It generates TSDoc/JSDoc for TypeScript code with proper parameter descriptions, return types, and usage examples. It creates changelogs from conventional commit messages, grouping entries by Added/Fixed/Changed. It audits existing documentation for staleness and gaps -- finding README sections that describe features that no longer exist, API docs that do not match implemented endpoints, and public functions that lack docstrings.

What makes this agent more than "add a comment above each function" is its understanding of documentation quality. It writes TSDoc that explains the why, not the what. A function called calculateHealthScore does not need a docstring that says "Calculates the health score." It needs one that explains the weighted formula, the input ranges, and a usage example that shows real values. The Docs agent generates this level of documentation because it reads the implementation, understands the logic, and writes descriptions that a newcomer would find useful.

The agent also performs documentation audits. It scans all public exports and reports a coverage metric: documented / total public APIs. It flags documentation older than 30 days for review. It compares README sections against the actual project structure and reports discrepancies. This turns documentation from a "we should do this someday" task into a measurable quality dimension with a concrete number to improve.

When to Use It

  • After adding new components or services: When new code has been written and needs comprehensive TSDoc documentation with parameter descriptions and examples.
  • Before a release: When you need a changelog generated from conventional commits covering everything since the last version tag.
  • When documentation feels stale: When you suspect the README, API docs, or architecture guides no longer match the actual codebase and need an audit.
  • When onboarding a new team member: When you need documentation coverage increased across the codebase so newcomers can understand the code through its docs.

Read the full file on GitHub · 157 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 · 157 lines · 0 tokens per session scan A 81add9058283

Subscribe to this mod's changes

docs is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,926 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 2026-08-31.