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 atretyak1985/swarmery --skill write-articlegit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/write-article)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/write-article"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/write-article/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/atretyak1985/swarmery/write-article"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/write-article.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 | $0.00108 | $0.02053 |
| Opus 5.5 | $0.00043 | $0.00821 |
| Sonnet 5.5 | $0.00022 | $0.00411 |
| Haiku 4.5 | $0.00011 | $0.00205 |
Grade A, and why
write-article 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an article
An article about this project needs two kinds of material. The author holds one: why something was built, what went wrong on the way, what they now believe. The repository holds the other: the numbers, names and dates the author would misremember. This skill gets the first by interviewing the author and the second by reading, and puts nothing into the article that came from neither.
The layout, the front matter and what each outlet's editor drops are in
articles/README.md. The author's voice and standing facts are in
articles/STYLE.md once the first interview has written it.
1. Research before asking
articles/README.md,articles/STYLE.md, and the front matter of every existing article, so the new one neither repeats an old one nor misses a chance to link to it.- The direction itself, in the repository: code,
docs/,CHANGELOG.md, ADRs,git log, merged PRs. Keep a fact sheet as you go, one line per fact with where it comes from (path:line, commit, PR number). - What the outlet's readers have been reading on this subject. Search the web
for what was published on it in about the last month, on the target outlet
first, and on all of them while the outlet is still open. dev.to has a public
listing,
https://dev.to/api/articles?tag=<tag>&top=30, which returns a tag's posts from the last 30 days with their reaction and comment counts. Substack and Medium have none, so search by topic restricted to the site. For each post that matters, note the title, author, date, link, its claim in one line, and how it was received where that is visible. Then write down what these posts agree on, what they argue about, and what none of them has said.
The repository research decides the quality of the interview. It removes every question the repository can answer, and it turns the rest from generic ("what challenges did you face?") into specific ("PR #355 fixed an 11-hour hang; is that the story here, or a footnote?").
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 · 158 lines · 108 tokens per session scan A 8faef371559c
write-article is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 108 tokens to every session and 2,053 once invoked, about $0.0004 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 2026-10-07.
Other skills, from other repositories
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
style-ops
Maintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.