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 aeonfun/aeon --skill skill-articlegit clone --depth 1 https://github.com/aeonfun/aeonWrote 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/aeonfun/aeon/skill-article)<a href="https://agentmods.dev/skills/aeonfun/aeon/skill-article"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/skill-article.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02057 |
| Opus 5 | $0.00033 | $0.01028 |
| Sonnet 5 | $0.00013 | $0.00411 |
| Haiku 4.5 | $0.00007 | $0.00206 |
Grade A, and why
skill-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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skill-article — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
${var} — Selector:
<skill-name> [--brand <handle>] [--banner].
<skill-name>→ announce that skill (must exist underskills/<skill-name>/).- empty → pick the most article-worthy skill from the last 14 days of
memory/logs/: prefer a skill that shipped recently, produced verified output, or hit a milestone. If nothing qualifies, logSKILL_ARTICLE_NO_TARGET, send no notification, and exit clean.--brand <handle>anywhere → byline/handle for the outreach footer (default: this instance's public identity fromsoul/, else the repo's org).--banneranywhere → also generate one 16:9 title banner through the Higgsfield MCP (spends credits; see Step 5). Off by default - a blank run never spends.Examples:
"aeon-update","rug-scan --brand @myproject --banner".
Today is ${today}. Write a launch article for one skill, modeled on the security-industry "skill announcement" format: the article sells the insight the skill encodes, not the file - and then gives the file away.
Shared preamble
- Read
memory/MEMORY.mdand the last 14 days ofmemory/logs/- know what this skill has actually done. - If a
soul/directory exists, readsoul/SOUL.mdandsoul/STYLE.mdfor voice. Default voice: terse, declarative, builder-wrote-this-fast. - Read the target's full
skills/<name>/SKILL.md. Every claim in the article must trace to a line in it.
Step 1 — Mine the track record (real numbers only)
Hunt for countable proof before writing a word:
memory/logs/entries under the skill's### <name>headings: runs, OK/error statuses, notable outcomes.output/files the skill produced; PRs or issues it opened (gh pr list --search).git log -- skills/<name>/for ship date and iteration history.
A real stat ("84 verified findings", "31 runs, 0 false alarms") becomes the headline. If no real count exists, the headline uses the mechanism instead. Never invent a number - a fabricated stat is the one thing that kills this format.
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.
- 3d ago First seen · 107 lines · 66 tokens per session scan A 7826b9d27920
skill-article is a skill published in the GitHub repository aeonfun/aeon (718 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 2,057 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 2026-09-05.
Other skills, from other repositories
flowcraft-config
Author, validate, and troubleshoot complete FlowCraft deployment configuration (deploy.yaml with the runtime section, inference/workspace/sandbox/tool sub-documents, core/memory contracts, and graph JSON node wiring). Use when writing or reviewing FlowCraft configs, assembling an agent deployment, adding…
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
unit-converter
Converts values between metric and imperial units, using the project's agreed factors.
explore
Explore the codebase and summarize how the project is wired.
flow-define
Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase). Use when: AUTOMATICALLY ACTIVATE when user requests clarification or scoping:. "define the requirements for X". "clarify the scope of Y".
flow-develop
Multi-AI implementation using Codex and Gemini CLIs (Double Diamond Develop phase). Use when: AUTOMATICALLY ACTIVATE when user requests building or implementation:. "build X" or "implement Y" or "create Z". "develop a feature for X".