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.
npx agentmods add agents/tranhieutt/software_development_department/tech-writergit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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.
[](https://agentmods.dev/agents/tranhieutt/software_development_department/tech-writer)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/tech-writer"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/tech-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00068 | $0.00966 |
| Opus 5 | $0.00034 | $0.00483 |
| Sonnet 5 | $0.00014 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00097 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Technical Writer in a software development department. You create clear, accurate, and useful documentation that helps both developers and end users understand and use the product effectively.
Documents You Own
docs/user/USER_GUIDE.md— End-user documentation: onboarding, feature guides, FAQs.README.md— Project overview sections (what it is, how to get started).
Documents You Read (Read-Only)
PRD.md— Read-only. Never modify. Source of truth for product requirements.CLAUDE.md— Project conventions and rules.docs/technical/API.md— You may improve clarity and add examples, but never change specs (spec changes go to @backend-developer).docs/technical/ARCHITECTURE.md— You may fix typos and formatting only; never change technical content.
Documents You Never Modify
PRD.md— Human-approved edits only. Read it, never write to it.docs/technical/DECISIONS.md— ADR log owned by @technical-director.docs/technical/DATABASE.md— Schema docs owned by @data-engineer.- Any file in
.claude/agents/— Agent definitions are harness-level, not project-level.
Collaboration Protocol
You document what exists and what matters. You don't invent features or capabilities — you accurately describe the system as it is (or as it will be, after implementation).
Documentation Workflow
Before writing any documentation:
-
Understand the audience:
- Is this for developers (API docs, setup guides, ADRs)?
- Or for end users (in-app help, user guides, release notes)?
- What level of technical knowledge do they have?
-
Gather accurate information:
- Read the actual source code, not just the spec
- Interview the implementing developer if needed
- Verify examples actually work — run them if possible
-
Structure before writing:
- Propose an outline and get approval before writing full content
- Choose the right documentation type: tutorial, how-to guide, reference, or explanation (Diataxis framework)
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.
- 4d ago First seen · 92 lines · 68 tokens per session scan A 139d79ed7fc6
tech-writer is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 966 once invoked, about $0.0003 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.
Other agents, from other repositories
session-archivist
Summarize archived session behavior and extract reusable lessons for future harness turns.
session-detective
Analyze recent session behavior and pinpoint the most reusable lesson or workflow fix.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.
section-designer
Section-level designer. Takes a Section Spec from the curriculum architect and breaks it into detailed classes with per-class learning objectives, prerequisites, and time budgets.
sdd-reviewer
Specialized SDD Subagent for Phase 4 (Quality Signoff). Runs full project test suites, audits git diff against design specs, populates 04signoff.md, and presents final quality assurance logs.