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 skills add dork-labs/dorkos --skill writing-blog-postsgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/skills/dork-labs/dorkos/writing-blog-posts)<a href="https://agentmods.dev/skills/dork-labs/dorkos/writing-blog-posts"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-blog-posts/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/skills/dork-labs/dorkos/writing-blog-posts"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-blog-posts.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 | $0.00066 | $0.06493 |
| Opus 5 | $0.00033 | $0.03247 |
| Sonnet 5 | $0.00013 | $0.01299 |
| Haiku 4.5 | $0.00007 | $0.00649 |
Grade A, and why
writing-blog-posts 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 9d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Blog Posts
The blog at blog/*.mdx holds 61 posts and every one of them is a release note. The tutorial, announcement, and news categories are declared in the schema, styled with their own colors, and have never been used. Whatever you are about to write is the first of its kind, not the sixty-second of an existing kind.
The gate, before you write a sentence
A blog post is exactly where an unverified claim slips out. AGENTS.md:7:
"In user-facing copy, docs, and release notes, never state that a still-unverified surface or pillar ... works (the demo-claim gate:
meta/positioning-202607/09-gtm-plan.md§2.0)."
Under the gate right now, per that same line:
| Surface | Status |
|---|---|
| Obsidian plugin | Built but under-tested |
| Windows x64 desktop | Early alpha, never confirmed by a real end-user install |
| Mesh+Relay multi-agent coordination | Shipped, unverified end to end |
| Marketplace Claude-Code-superset compatibility | Shipped, unverified end to end |
| Linux desktop | Does not exist. Not gated, absent |
Room slash commands, post_to_room everywhere |
Designed, not built (specs/rooms/02-specification.md:628-706) |
Clear of the gate: the web cockpit via CLI install, and the macOS desktop app (signed, notarized, downloadable).
AGENTS.md is the live list. 09-gtm-plan.md §2.0 is the rule behind it and is older, so where the two disagree, AGENTS.md wins.
The instruction, and it is not optional. Go through the finished draft one capability claim at a time. For each one, name the artifact that proves it shipped and was verified: a merged PR, a changelog fragment, a browser test, a docs page describing it as it works today. If you cannot find one, rewrite the sentence in the future tense or cut it. "DorkOS agents coordinate across machines" and "we are building toward agents that coordinate across machines" are different claims, and only one of them is currently true.
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.
- 9d ago First seen · 289 lines · 66 tokens per session scan A 99ebb83e0681
writing-blog-posts is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 6,493 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.