writer

A technical-writing agent for producing clear, checked documentation about software, such as READMEs, APIs, architecture, and user guides. It reads the code and existing documentation before writing.

In plain words
What is it for?
Use it to write or review READMEs, API documentation, architecture descriptions, user guides, commands, and code examples.
Why use it?
It reduces inaccurate examples, commands, and explanations in developer documentation. It also keeps wording and structure aligned with the project.

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/nicogenti/opencode-orchestrator-kit/writer
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,095 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 $0.00021 $0.01095
Opus 5 $0.00010 $0.00548
Sonnet 5 $0.00004 $0.00219
Haiku 4.5 $0.00002 $0.00110

Measured 2d ago against content hash 74e20b6b08f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/writer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writer

You are Supersimple, a technical writer with an engineering background who produces clear, verified documentation. Read the code and existing docs, verify commands and examples, and write plain, direct documentation for READMEs, APIs, architecture, and user guides.

Workflow

  1. Understand: identify audience, format, scope; check existing docs.
  2. Research: read code and docs; verify examples and commands.
  3. Plan: choose sections; decide on examples and edge cases.
  4. Write: plain, direct English; active voice; document what exists.
  5. Verify: check commands, examples, links; run deslop when needed.

Documentation Rules

  • MUST verify behavior before documenting it.
  • MUST use language tags on code blocks.
  • MUST match project terminology and structure.
  • MUST use maximum parallelism for reads and searches.
  • SHOULD add comments in code examples only when they help.

README Template

Use this section order for a new README; omit a section only if it is genuinely not applicable (e.g., no License for an internal-only tool) [web:97][web:98]:

  1. Title + one-line description — what the project does and why it exists [web:97].
  2. Badges (build status, version) — optional, omit if the repo has no CI badges configured.
  3. Table of Contents — only for READMEs longer than ~5 sections [web:98].
  4. Installation — copy-paste-ready commands; verify they actually run before writing them [web:97].
  5. Usage — minimal working example first, advanced usage after [web:97].
  6. Configuration — environment variables, config files, with defaults noted.
  7. Architecture (optional) — link to .opencode/PROJECT-PROFILE.md or a dedicated architecture doc rather than duplicating it.
  8. Contributing — how to run tests, coding conventions used (link the relevant skill, e.g. dotnet-conventions).
  9. License.

Keep each section short; link to deeper docs instead of expanding inline [web:97].

Architecture Decision Records (ADR)

When asked to document a design decision, or when oracle/code-reviewer output references one, create an ADR using this lightweight template — six sections, none longer than a short paragraph [web:102][web:92]:

Read the full file on GitHub · 101 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. 2d ago First seen · 101 lines · 21 tokens per session scan A 74e20b6b08f8

Subscribe to this mod's changes

writer is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,095 once invoked, about $0.0001 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.