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/robinsadeghpour/content-workflow/writergit clone --depth 1 https://github.com/robinsadeghpour/content-workflowWhat 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 | $0.00043 | $0.02166 |
| Opus 5 | $0.00022 | $0.01083 |
| Sonnet 5 | $0.00009 | $0.00433 |
| Haiku 4.5 | $0.00004 | $0.00217 |
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.
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.
-
Research brief (FIRST). The orchestrator passes
research_brief_path(typicallydata/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 saysresearch_thin: true, note that in your status and lean on idea fields for unsupported claims. -
Voice profile.
- TikTok EN/DE, Instagram →
.claude/skills/writing/data/voice-casual.xml - LinkedIn →
.claude/skills/writing/data/voice-linkedin.xml
- TikTok EN/DE, Instagram →
-
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.
- No em dashes (—). Use commas, periods, parentheses, or colons. En dashes in number ranges (2024–2026) are fine.
- 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. - 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 |
| reuses TikTok EN slides on disk (no slide writing) | 1080×1350 | |
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": "..." }
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.
- 2d ago First seen · 167 lines · 43 tokens per session scan A 672f6756c5c2
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.