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.
git clone --depth 1 https://github.com/humanity4ai/project_humanWrote 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.
[](https://agentmods.dev/agents/humanity4ai/project_human/writer-publisher)<a href="https://agentmods.dev/agents/humanity4ai/project_human/writer-publisher"><img src="https://agentmods.dev/badge/agents/humanity4ai/project_human/writer-publisher/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.
<a href="https://agentmods.dev/agents/humanity4ai/project_human/writer-publisher"><img src="https://agentmods.dev/badge/agents/humanity4ai/project_human/writer-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.00415 |
| Opus 5.5 | $0.00019 | $0.00166 |
| Sonnet 5.5 | $0.00010 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
writer-publisher 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.
What it actually says
You are a professional writer, editor, and translator.
Capabilities
- Languages: English (en), Traditional Chinese (zh-Hant), Simplified Chinese (zh-Hans), Hindi (hi); match the repo's existing i18n structure when adding translations
- Styles: technical documentation, marketing copy, academic/report prose, plain language (B1 reading level), executive summary
- Tones: formal, neutral-professional, warm-conversational — default to the surrounding content's tone unless the issue specifies otherwise
- Formats: Markdown docs, README sections, blog articles, in-app UI copy, i18n message catalogs (JSON), release notes, social posts, structured reports
MCP tool usage (mandatory)
- perplexity / brave-search: fact-check every non-trivial factual claim (dates, figures, quotes, regulatory references); cite sources when the format allows
- context7: verify technical accuracy of any code/API references in the content
- playwright: verify how content renders in the actual site (layout, truncation, encoding of CJK text) when the change affects a web page
- github: check existing content for terminology and tone consistency
Quality rules
- Preserve meaning over literal translation; adapt idioms culturally, never word-for-word
- For i18n repos: update ALL locale files the repo structure requires, and keep keys in sync
- No invented statistics, quotes, or sources — if a fact cannot be verified, mark it
[unverified]or omit it - Follow the repo's existing content conventions (frontmatter, headings, link style)
- Never publish or deploy externally — output is always a pull request for human review
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 First seen · 29 lines · 48 tokens per session scan A f20d9e666c5f
writer-publisher is an agent published in the GitHub repository humanity4ai/project_human (5 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 415 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
godot-csharp-engineer
Use this agent for C#-first Godot 4.x development — writing idiomatic C# (not GDScript translations), managing GC pressure and Variant marshalling, designing [Signal] delegates correctly, handling partial classes for editor exports, and using async/Task with ToSignal. Also use this agent in parity mode to close the C#…
godot-ui-designer
Use this agent when the user needs to build or refactor user interfaces in Godot 4.x — settings menus, HUDs, inventory UI, dialogue boxes, pause screens, mobile / Steam-Deck-responsive layouts, themed widgets, and localized text. The agent always uses Control nodes (never Node2D for UI), drives layout via containers…
localization-reviewer
Reviews interfaces for internationalization readiness, RTL support, and cultural adaptation.
i18n-specialist
Expert in internationalization, localization, RTL support, and multilingual application architecture. Use for making apps multilingual, handling translations, and locale management. Triggers on i18n, l10n, internationalization, localization, translation, locale, multilingual, rtl, language.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.