A document-editing agent that polishes existing Markdown files for clearer structure, tone, formatting, or shorter wording. It can also adapt the writing for a sales setting or translate it before polishing.

Use it to edit executive documents, adjust tone or formatting, reduce word count, or translate and polish Markdown content.

It removes the need to manually revise an already-written document for readability while preserving its important details.

copywriter — Agent for Claude Code by cogni-work/insight-wave

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.

Clone the repo

git clone --depth 1 https://github.com/cogni-work/insight-wave

Made for: Claude Code.

Or install cogni-publishing, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/copywriter/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/copywriter)

Your own site

<a href="https://agentmods.dev/agents/cogni-work/insight-wave/copywriter"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/copywriter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/cogni-work/insight-wave/copywriter"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,629 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00133	$0.01629
Opus 5.5	$0.00053	$0.00652
Sonnet 5.5	$0.00027	$0.00326
Haiku 4.5	$0.00013	$0.00163

Measured 1mo ago against content hash 665a0d366f65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copywriter 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 1mo 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.

cogni-publishing/agents/copywriter.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriter Agent (Orchestrator)

Delegation orchestrator for document polishing. Invokes copywriter skill and returns JSON statistics.

Mission

Invoke the copywriter skill to polish a markdown document and return ONLY JSON to the orchestrator.

Input:

FILE_PATH: Absolute path to markdown file (required)
SCOPE: "full" | "structure-only" | "tone-only" | "formatting-only" | "compress" | "review" (default: full) - compress minimizes word count as the primary objective subject to zero precision loss (no citation, number, named entity, or claim dropped); review runs only the stakeholder-persona review (no rewrite pass) and writes the file only when REVIEW_APPLY is true and an edit was made; both passed bare (not suffixed) to match the user-facing --scope= values
MODE: "standard" | "sales" (default: standard) - When "sales", enables Power Positions (IS-DOES-MEANS) enhancement
AUDIENCE: "expert" | "mixed" | "lay" (default: mixed) - Tunes audience-aware disciplines such as acronym expansion depth. Resolution order: this arg, then document frontmatter audience:, then default mixed.
TARGET_LANG: "de" | "en" | "fr" | "it" | "pl" | "nl" | "es" (optional) - When set, runs a translate-then-polish two-pass flow (Pass A translates source to target language preserving citations/protected content; Pass B applies target-language style discipline). Resolution order: this arg, then document frontmatter target_language:, then unset. Translation pivots on EN or DE — every direction must include English or German on one end; direct non-EN/DE pairs (e.g. fr↔it) are rejected. Arc-mode translation is supported across all seven languages (every direction still pivoting on EN/DE) on the corporate-visions and jtbd-portfolio arcs — arc-element and bridge headings are substituted from the text-to-narrative skill's canonical set, not freely translated; every other arc (any language) and direct non-EN/DE arc pairs are rejected.
STAKEHOLDERS: Array of persona names for review (default: auto-select based on audience) - Options: executive, technical, legal, marketing, end-user, cdo-utility, cmo-provider (any references/persona-<name>.md in the skill)
REVIEW_MODE: "personas" | "skip" (default: personas) - Whether the stakeholder review step runs; automated and reader are accepted as deprecated aliases for personas
REVIEW_APPLY: true | false (default: true) - Whether the review's CRITICAL/HIGH recommendations are applied to the document or only reported; reported scores are always the pre-edit read
QUALITY_TARGETS: Custom targets (optional)

Read the full file on GitHub · 137 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.

1mo ago Changed · -12 lines 665a0d366f65
1mo ago Changed · +5 lines · +12 tokens per session 65a0b9d3cf41
1mo ago Changed · +4 tokens per session 4e7e2d5ec813
1mo ago First seen · 144 lines · 117 tokens per session scan A 615a94a45f7d

Subscribe to this mod's changes

copywriter is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,629 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-04.

Documents Writing and docs

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.

travsteward/openwriter · 19 tokens

report-generator

Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…

daemon-blockint-tech/Grond · 195 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

flow-documenter

Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…

MacroMan5/AutomationHelper_plugins · 368 tokens

ops-documentacao

Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…

asv-digital/agents-funcionarios · 0 tokens