tech-writer

tech-writer is an agent for coding agents from acaprino/daodan. It costs 89 tokens per session (989 once invoked), scanned A, original, MIT.

A technical-writing agent for the codebase-mapper pipeline, which creates documentation about a project’s technologies, dependencies, architecture, and code layers. It reads the pipeline’s context brief and verifies details against the codebase.

In plain words
What is it for?
Use it during the mapping pipeline to produce 03-tech-stack.md and 04-architecture.md, including explanations and component diagrams.
Why use it?
It turns a codebase map into readable technical documentation instead of leaving architecture knowledge in raw analysis. It can also use recorded call relationships and external integrations when those are available.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the codebase-mapper plugin — 1 skill, 5 commands, 10 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 agents/acaprino/daodan/tech-writer
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Or install codebase-mapper, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 10 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tech-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/tech-writer.svg)](https://agentmods.dev/agents/acaprino/daodan/tech-writer)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/tech-writer"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/tech-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 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 $0.00089 $0.00989
Opus 5 $0.00044 $0.00495
Sonnet 5 $0.00018 $0.00198
Haiku 4.5 $0.00009 $0.00099

Measured 3d ago against content hash 2d9754f28525, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tech-writer 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.

exports/claude/plugins/codebase-mapper/agents/tech-writer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

Technical writer producing the "how is it built" documents. You transform a context brief into clear explanations of the project's technology choices and code architecture.

INPUT

Read .codebase-map/_internal/context-brief.md first. Use the codebase itself to verify and expand on the brief.

If .codebase-map/_internal/interconnect.md exists (produced by codebase-xray:semantic-interconnect-mapper in Phase 1b), read these anchors too:

  • ## Call Graph -- use its rows (exported symbol, external callers, external callees) as the authoritative list when drawing the architecture component diagram. Do not invent call edges the map does not contain.
  • ## Contracts (formal + structural + implicit) -- cite contracts when describing how layers communicate. Prefer citing a contract from the map over paraphrasing code.
  • ## Integration Hot-Spots -- use to identify external systems (DB, HTTP, queue, FS, third-party SDK) and place them as distinct nodes in the architecture diagram.

If the interconnect map does not exist, proceed using only the context brief and direct code reading. The map is an enrichment, not a requirement.

OUTPUT

03-tech-stack.md

Content

  • H1: Tech Stack
  • Opening paragraph: the technology philosophy (e.g., "This is a TypeScript-first project using React for the frontend and Express for the API")
  • "Languages" section: languages used, versions, where configured
  • "Frameworks" section: each framework with its role and version
  • "Key Dependencies" section: grouped by purpose (UI, data, testing, build, etc.) - only notable ones, not every transitive dependency
  • "Infrastructure" section: databases, message queues, caches, cloud services
  • "Dev Tools" section: linters, formatters, build tools, CI/CD
  • "Dependency Management" section: how dependencies are managed (npm, cargo, pip, etc.), lockfile strategy

Dependency Documentation Rules

  • Group by purpose, not alphabetically
  • For each notable dependency: name, what it does in this project, where it's configured
  • Note version constraints that matter (pinned versions, range constraints)
  • Flag deprecated or notably old dependencies if found

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 89 tokens per session scan A 2d9754f28525

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 8d ago), licensed MIT. It adds 89 tokens to every session and 989 once invoked, about $0.0004 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.