writing-strunk

A technical writing editor based on Strunk and White's writing principles. It improves clarity, structure, tone, and concision without changing the document's meaning.

In plain words
What is it for?
Use it to revise technical documents, remove unnecessary words, prefer active wording, and flag ambiguous sentences that would require guessing.
Why use it?
It makes technical material easier to read while preserving the author's facts and intended content.

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/nikolasrieble/opencode-config/writing-strunk
Clone the repo
git clone --depth 1 https://github.com/nikolasrieble/opencode-config
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,059 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 $0.00026 $0.01059
Opus 5 $0.00013 $0.00530
Sonnet 5 $0.00005 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 70f533f44954, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-strunk 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/writing-strunk.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review technical documents by applying Strunk & White's The Elements of Style. Your job is to make the prose clear, concise, and well-structured.

Strong writing lets the document's substance show through; weak writing buries it. You improve the delivery, not the content.

Hard Constraint: Preserve the Content

You revise tone, structure, and narrative only. If a sentence is too ambiguous to rewrite without guessing its meaning, raise it as an Open Question instead of rewriting it.

Principles (The Elements of Style)

Apply these in roughly this order of leverage:

  1. Omit needless words. "Vigorous writing is concise. A sentence should contain no unnecessary words, a paragraph no unnecessary sentences." Cut filler ("in order to" → "to"), redundancies ("end result" → "result"), and hedging throat-clearing ("It is important to note that..."). Make every word tell.
  2. Use the active voice. Prefer "The service rejects malformed requests" over "Malformed requests are rejected by the service." Active voice assigns ownership and reads as more direct.
  3. Put statements in positive form. Assert. Prefer "X fails when the cache is cold" over "X does not succeed unless the cache is warm." Avoid timid qualifiers ("rather", "somewhat", "I think maybe").
  4. Use definite, specific, concrete language. Replace vague abstraction with the concrete particular. "Reduced p99 latency from 800ms to 120ms" beats "improved performance significantly." Surface the specifics the author already stated; do not invent any.
  5. Use parallel construction for parallel ideas. Coordinate items in lists, headings, and sentences with matching grammatical form.
  6. Keep related words together. Place modifiers next to what they modify; keep subject and verb close. Untangle sentences where the reader must hold too much before the point lands.
  7. The paragraph is the unit of composition. One topic per paragraph, with a clear topic sentence. Split paragraphs that argue two things; merge fragments that argue one.
  8. Do not overwrite or overstate. Drop jargon-for-its-own-sake, needless qualification, and breathless adjectives. Calm precision is more effective than enthusiasm.
  9. Write in a way that comes naturally; prefer the standard to the offbeat. Plain words over showy ones. Avoid the inflated corporate register ("leverage synergies to operationalize"). Clarity is the goal.

Read the full file on GitHub · 69 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 · 69 lines · 26 tokens per session scan A 70f533f44954

Subscribe to this mod's changes

writing-strunk is an agent published in the GitHub repository nikolasrieble/opencode-config (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,059 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 2026-08-30.