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 larsboes/Axon --skill writing-skillsgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/writing-skills)<a href="https://agentmods.dev/skills/larsboes/axon/writing-skills"><img src="https://agentmods.dev/badge/skills/larsboes/axon/writing-skills/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/larsboes/axon/writing-skills"><img src="https://agentmods.dev/badge/skills/larsboes/axon/writing-skills.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 | $0.00106 | $0.01983 |
| Opus 5 | $0.00053 | $0.00992 |
| Sonnet 5 | $0.00021 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
writing-skills scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- discovery roots: `ls -d ~/.claude/skills <project>/.claude/skills 2>/dev/null` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
Build a skill a zero-context mid-level engineer or Sonnet-class model can load and execute correctly on the first try. Discoverable metadata, lean body, deterministic scripts. Ground truth only: verify every path/command against disk before writing it — a wrong runbook is worse than none.
Before you scaffold
Write a skill when the same instructions get pasted into chat repeatedly, or a CLAUDE.md section has grown into a procedure rather than a fact — a skill's body loads only when triggered, so it costs nothing until used. Don't write one for a single unrepeated task, or to store a fact with no procedure attached (that's a references/ note inside an existing skill, or CLAUDE.md itself, not a new skill).
Variables — instantiate before writing
| var | fill with | constraint |
|---|---|---|
<name> |
the skill id | ^[a-z0-9]+(-[a-z0-9]+)*$, ≤64, == its directory basename, no anthropic/claude |
<desc> |
the trigger sentence | 3rd person, ≤1024, what + "Use when …" + "Do not use for …" |
<dir> |
.claude/skills/<name> (project) or ~/.claude/skills/<name> (personal) |
the two discovery roots |
<freedom> |
low | medium | high per step |
fragile/safety → low · preferred-pattern → medium · open-ended → high |
<body_max> |
500 |
hard line ceiling for SKILL.md |
<ref_depth> |
1 |
references stay this many hops from SKILL.md |
<folders> |
scripts references assets |
the only subdirs, each one level deep |
Loading model — earn every token
| level | loaded | budget | holds |
|---|---|---|---|
| 1 metadata | always | ~100 tok/skill | <name>+<desc>, the trigger |
| 2 body | on trigger | <<body_max> lines |
workflow + the few rules a smart model can't infer |
3 <folders> |
on read/run | ~∞ (scripts: only stdout costs tokens) | schemas, long docs, deterministic tools |
Bulk lives in Level 3; SKILL.md is its table of contents. Full model + surface differences: references/architecture.md.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/SKILL.template.md 1.1 KB
- references/architecture.md 2.5 KB
- references/best-practices.md 5.4 KB
- references/bootstrap-library.md 4.7 KB
- references/checklist.md 1.9 KB
- references/claude-code-extensions.md 5.4 KB
- references/evaluation.md 2.1 KB
- references/patterns.md 2.5 KB
- scripts/validate_metadata.py 5.5 KB runs code
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.
- 10d ago First seen · 74 lines · 106 tokens per session scan A 2e3df6771416
writing-skills is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,983 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.