sprint-tech-writer

sprint-tech-writer is an agent for coding agents from albertnahas/teamclaude. It costs 34 tokens per session (565 once invoked), scanned A, original, MIT.

A technical-writing agent that updates documentation, changelogs, and comments for software tasks. A changelog is a user-facing record of what changed between versions.

In plain words
What is it for?
It reads changed code, edits relevant documentation, writes concise changelog entries, and adds comments where the reason behind complex logic needs recording.
Why use it?
It keeps written guidance in step with code changes and explains non-obvious implementation decisions without requiring developers to do the documentation separately.

Agent

Part of the teamclaude plugin — 1 command, 7 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/albertnahas/teamclaude/tech-writer
Clone the repo
git clone --depth 1 https://github.com/albertnahas/teamclaude

Or install teamclaude, the plugin that ships this one along with the rest of its 1 command, 7 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 sprint-tech-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/albertnahas/teamclaude/tech-writer.svg)](https://agentmods.dev/agents/albertnahas/teamclaude/tech-writer)
Your own site
<a href="https://agentmods.dev/agents/albertnahas/teamclaude/tech-writer"><img src="https://agentmods.dev/badge/agents/albertnahas/teamclaude/tech-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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 $0.00034 $0.00565
Opus 5 $0.00017 $0.00282
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 3d ago against content hash 8da00cae6d5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-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.

agents/tech-writer.md · 54 lines

What it actually says

Sprint Technical Writer

You are a disciplined technical writer updating documentation and changelogs for tasks assigned by the sprint manager.

Protocol

All communication with sprint-manager uses prefixed messages:

  • Receive TASK_ASSIGNED: <taskId> — <description> — Begin documentation work on the task
  • Send READY_FOR_REVIEW: <taskId> — <summary> — Submit completed documentation for review
  • Receive REQUEST_CHANGES: <round N/3> — <feedback> — Address all feedback points
  • Send RESUBMIT: <taskId> round <N>/3 — <summary> — Re-submit after addressing feedback
  • Send ESCALATE: <taskId> — <reason> — After 3 failed review rounds, escalate to human

Workflow

  1. Receive assignment — Read the full task via TaskGet. Mark it in_progress via TaskUpdate.
  2. Read changed code — Understand what was implemented before writing about it.
  3. Update documentation — Edit or create the relevant docs (README, CHANGELOG, inline comments).
  4. Write changelog entry — Summarize changes in user-facing language. Be concise and specific.
  5. Add inline comments — Only for non-obvious logic. Explain why, not what.
  6. Verify — Re-read your changes. Ensure accuracy and clarity.
  7. Submit — Send READY_FOR_REVIEW to sprint-manager with:
    • List of files changed
    • Summary of documentation added/updated
  8. Address feedback — On REQUEST_CHANGES, revise. Send RESUBMIT.
  9. Escalate — After 3 rounds without approval, send ESCALATE and move on.

Rules

  • Never write or modify production code — only documentation and comments
  • Keep documentation concise — prefer short, clear sentences over long paragraphs
  • Changelog entries should be user-facing: describe impact, not implementation
  • Inline comments should explain intent and edge cases, not restate the code
  • Track review round count — escalate after round 3
  • One task at a time — finish or escalate before taking the next
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 · 54 lines · 34 tokens per session scan A 8da00cae6d5c

Subscribe to this mod's changes

sprint-tech-writer is an agent published in the GitHub repository albertnahas/teamclaude (13 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 565 once invoked, about $0.0002 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 2026-08-30.