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 defuddlegit 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/defuddle)<a href="https://agentmods.dev/skills/larsboes/axon/defuddle"><img src="https://agentmods.dev/badge/skills/larsboes/axon/defuddle/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/defuddle"><img src="https://agentmods.dev/badge/skills/larsboes/axon/defuddle.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 | $0.00088 | $0.00694 |
| Opus 5.5 | $0.00035 | $0.00278 |
| Sonnet 5.5 | $0.00018 | $0.00139 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
defuddle 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 1mo 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.
This is a copy
100% identical to defuddle — 62 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
defuddle
Two ways to read a page as clean markdown. Prefer the first.
In pi: use fetch_content
pi has a native fetch_content tool, from the vendored pi-web-access extension. Use it:
one call rather than a shell command, nothing to install, and it also handles PDFs, GitHub
repositories and video transcripts, which the CLI does not.
Do not shell out to the CLI while that tool is available. It is the fallback, and reaching for it in pi costs a subprocess to do a worse job.
Otherwise: the defuddle CLI
For a harness with no fetch tool, this skill needs the CLI on PATH. It is installed
globally through its own release tooling, not vendored into Axon:
npm install -g defuddle # → $(npm prefix -g)/bin/defuddle
defuddle --version # expect 0.19.3 or newer
If defuddle is not found, that install is the fix — run it, rather than switching to a
fetch tool you do not have. Nothing else in Axon depends on it.
Usage
Always pass --md for markdown output:
defuddle parse <url> --md # readable content to stdout
defuddle parse <url> --md -o content.md # save it
defuddle parse <url> -p title # one metadata field
| Flag | Format |
|---|---|
--md |
Markdown — the default choice |
--json |
JSON carrying both HTML and markdown |
| (none) | HTML |
-p <name> |
one metadata property: title, description, domain, … |
Provenance
kepano/defuddle, MIT, by Steph Ango — see the
[defuddle] row in upstreams.toml. It sits alongside the same author's
kepano/obsidian-skills, which Packs/knowledge/LICENSE covers; these are two different
repositories with two separate notices, and only the second is vendored.
One thing not to "fix" later
The defuddle library also ships inside the vendored pi-web-access, which imports it as a
dependency for its own extraction path. That is a different role, not a duplicate: an extension
needs a module it can import, and this skill needs a command on PATH. Collapsing either into
the other makes it fragile — node_modules is wiped and reinstalled, a global binary is not.
Both are pinned to the same version on purpose. If they drift, one path renders pages with a
different extractor than the other, so move them together or not at all.
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.
- 1mo ago Changed · +22 lines · +14 tokens per session bb2c607340fd
- 1mo ago First seen · 42 lines · 74 tokens per session scan A 10673a4dc70a
defuddle is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 694 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to defuddle, differing in 62 lines, and is treated as a copy.
Other skills, from other repositories
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
bo-process-optimization
A method for examining a business workflow to find waiting, rework, handoff waste, and other delays, then proposing improvements and ways to measure them. It separates observed facts from possible explanations and suggestions.
starcat-ui-prototype
A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.
llm-wiki
Build and maintain a workspace-local, Obsidian-friendly research vault using Karpathy's LLM Wiki pattern.
simplify
Improve existing work with focused simplification passes across code, writing, research, operations, or general tasks.