suggest-skills

suggest-skills is a skill for Claude Code from larsboes/Axon. It costs 152 tokens per session (1,412 once invoked), scanned A, original, MIT.

A read-only reviewer of your past prompts and installed skills that looks for repeated work and repeated corrections. It proposes skills worth building and shows the evidence behind each suggestion.

In plain words
What is it for?
Use it to examine recent work, remove noisy patterns, compare findings with existing skills, and produce a ranked shortlist of new skill ideas.
Why use it?
It helps find recurring problems without relying on memory or guessing what would be useful. It does not create, edit, or install skills.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness plugin — 3 skills shipped together

Good fit Use it to examine recent work, remove noisy patterns, compare findings with existing skills, and produce a ranked shortlist of new skill ideas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larsboes/axon/suggest-skills
Install

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.

Any agent
npx skills add larsboes/Axon --skill suggest-skills
Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for suggest-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/larsboes/axon/suggest-skills/github.svg)](https://agentmods.dev/skills/larsboes/axon/suggest-skills)
Your own site
<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.

agentmods 80×15 button for suggest-skills

Your own site · 80×15
<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>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 7b306c6f43fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect-signals.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Packs/harness/skills/suggest-skills/SKILL.md · 102 lines

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".

Read the full file on GitHub · 102 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 102 lines · 152 tokens per session scan A 7b306c6f43fb

Subscribe to this mod's changes

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.