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.
git 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/plugins/larsboes/axon/writing)<a href="https://agentmods.dev/plugins/larsboes/axon/writing"><img src="https://agentmods.dev/badge/plugins/larsboes/axon/writing/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/plugins/larsboes/axon/writing"><img src="https://agentmods.dev/badge/plugins/larsboes/axon/writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
writing 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 today.
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.
What it actually says
{
"name": "writing",
"description": "Write for readers and for agents: human-voiced prose with a CI-gateable tell linter, and Claude agent skills authored to Anthropic + agentskills.io spec.",
"author": {
"name": "Lars Boes",
"url": "https://github.com/larsboes/Axon"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 338 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today First seen · 10 lines scan A 33f169c49835
writing is a plugin published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
lians
Bitemporal memory for Claude Code with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.
memtrace-skills
Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…
cortex
Remembers your decisions, coding conventions, and debugging lessons across every Claude Code session. Persistent local memory for AI coding agents.
promptline
Local, read-only visual timeline of your Claude Code prompt history - dashboard, activity heatmap, and searchable per-project/session feed. Binds to 127.0.0.1 only, no outbound network calls, nothing written back to /.claude.
fimemory
Local-first shared memory for AI tools. Plain files are the source of truth; relevant context is injected before your prompt instead of burned on agentic search loops.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.