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 suggest-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/suggest-skills)<a href="https://agentmods.dev/skills/larsboes/axon/suggest-skills"><img src="https://agentmods.dev/badge/skills/larsboes/axon/suggest-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/suggest-skills"><img src="https://agentmods.dev/badge/skills/larsboes/axon/suggest-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 | $0.00152 | $0.01412 |
| Opus 5 | $0.00076 | $0.00706 |
| Sonnet 5 | $0.00030 | $0.00282 |
| Haiku 4.5 | $0.00015 | $0.00141 |
Grade A, and why
suggest-skills 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
suggest-skills
One question: given what this person actually did, and where they had to repeat themselves, is there a recurring problem that deserves a skill and does not have one?
It proposes. Somebody else builds. This skill has no capability to create or edit a skill, and that is deliberate — a proposer that can also build grades its own homework.
Adapted from the SuggestSkills skill in LifeOS by Daniel Miessler (https://github.com/danielmiessler/LifeOS), MIT.
Procedure
Copy this checklist and track progress:
- [ ] 1. Gather the corpus with the script
- [ ] 2. Read the clusters and throw out the noise
- [ ] 3. Read the friction pairs
- [ ] 4. Dedup against what the skills actually do
- [ ] 5. Test each survivor against the bar
- [ ] 6. Rank, and say what evidence would change the ranking
1 — Gather. The model does not gather. Run:
bun scripts/collect-signals.ts --days 30 --json > /tmp/signals.json
--days N sets the window. --history PATH, --skills DIR and --packs DIR override the
sources; AXON_ROOT adds the Pack registry when it is set. Two runs over the same files return
the same corpus, which is what makes a proposal arguable instead of a mood.
Report every line in warnings to the user before using the output. A missing source is not a
detail: it changes what "no gap found" means.
2 — Read the clusters. Each cluster is prompts that share vocabulary, with sessions,
prompts, spanDays, the co-occurring words in with, and three samples. The grouping is lexical,
so some clusters are junk — a generic verb that survived the stoplist, or one long conversation
that recurs in three sessions because it was interrupted twice. Throw those out by reading the
samples. Keep a cluster only when the samples describe the same kind of work rather than the
same words. dominant lists the words too common to cluster: they name the corpus, and a proposal
whose whole content is a dominant word is a proposal to build a skill about "everything".
What ships with it
3 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.
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 · 102 lines · 152 tokens per session scan A 7b306c6f43fb
suggest-skills is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 1,412 once invoked, about $0.0008 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 2026-09-07.
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…
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.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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.