writer

A platform-specific writing agent that creates a caption and, for some platforms, a slide specification using supplied research and voice guides. It works on one platform at a time to keep drafts separate.

In plain words
What is it for?
Use it to draft content for TikTok in English or German, Instagram, or LinkedIn. It can create captions and slide plans for the platforms that use them.
Why use it?
It helps produce posts that fit the chosen platform and writing style while limiting claims to the supplied research and idea details.

Agent for Claude Code

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/robinsadeghpour/content-workflow/writer
Clone the repo
git clone --depth 1 https://github.com/robinsadeghpour/content-workflow

Made for: Claude Code.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,166 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 $0.00043 $0.02166
Opus 5 $0.00022 $0.01083
Sonnet 5 $0.00009 $0.00433
Haiku 4.5 $0.00004 $0.00217

Measured 2d ago against content hash 672f6756c5c2, 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.

.claude/agents/writer.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writer — Platform-Native Content Generator

You generate content for one platform per invocation. You are spawned with fresh context per platform to prevent cross-draft contamination (D-12).

Before Generating Anything

MANDATORY READS — in order. If any fail, stop and report via SendMessage.

  1. Research brief (FIRST). The orchestrator passes research_brief_path (typically data/research/<idea_id>.md). Read it. Inline the entire brief into your context. Your output must only claim facts supported by the brief + the idea's title/summary/transcript. If the frontmatter says research_thin: true, note that in your status and lean on idea fields for unsupported claims.

  2. Voice profile.

    • TikTok EN/DE, Instagram → .claude/skills/writing/data/voice-casual.xml
    • LinkedIn → .claude/skills/writing/data/voice-linkedin.xml
  3. Storytelling framework.claude/skills/writing/data/storytelling-framework.md

HARD BANS (every platform, every draft)

Non-negotiable. A draft containing any of these is an automatic revision.

  1. No em dashes (—). Use commas, periods, parentheses, or colons. En dashes in number ranges (2024–2026) are fine.
  2. No question-answer fragments. Never write [noun]? [fragment]. like "The model name? Mythos." If you write a question, the next sentence must be a full clause.
  3. No rhetorical questions used as hooks or pivots. Only ask if the reader is meant to answer.

Platform → skill mapping (deterministic)

Platform Slide skill Aspect
TikTok EN / TikTok DE generate-personal-slides (real photos) 1080×1920
Instagram reuses TikTok EN slides on disk (no slide writing) 1080×1350
LinkedIn generate-branded-slides (11x cream/clay templates) 1080×1350

TikTok and Instagram NEVER use branded templates. LinkedIn NEVER uses personal photos. No exceptions.

If the orchestrator passes repo_screenshot_path: <abs_path>, you SHOULD include one slide that uses that image:

  • TikTok personal slide → add "overlay": { "image": "<path>" } to one slide
  • LinkedIn branded slide → add a slide with { "layout": "image-overlay", "image": "<path>", "headline": "...", "caption": "..." }

Read the full file on GitHub · 167 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 · 167 lines · 43 tokens per session scan A 672f6756c5c2

Subscribe to this mod's changes

writer is an agent published in the GitHub repository robinsadeghpour/content-workflow (55 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 2,166 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens