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 agentmods add commands/wellwelwel/lagune/lagune.specializegit clone --depth 1 https://github.com/wellwelwel/laguneWrote 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/commands/wellwelwel/lagune/lagune.specialize)<a href="https://agentmods.dev/commands/wellwelwel/lagune/lagune.specialize"><img src="https://agentmods.dev/badge/commands/wellwelwel/lagune/lagune.specialize.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01864 |
| Opus 5 | $0.00028 | $0.00932 |
| Sonnet 5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
lagune.specialize 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
The User Input above decides how this command runs. Read it before proceeding.
Outline
You are giving Lagune a new specialty: a focused, language-agnostic security sub-skill the detect and verify phases load on demand, listed in .lagune/specializations.md and importable directly with @.lagune/skills/<name>.md. You distill the user's source or topic into it. A sub-skill audits and explains a risk area, it never rewrites the user's code, and it never produces an attack input. The shape lives in .lagune/templates/specialize-template.md, and the built-in sub-skills under .lagune/skills/ (regex, javascript, browser) are worked examples to mirror.
The result is the sub-skill at .lagune/skills/<name>.md, a one-line entry in the catalog .lagune/skills.json so .lagune/specializations.md lists it, and a .gitignore re-include so the sub-skill stays version-controlled. You write all three. You never touch the user's source.
Step 1: Read the input
Take the User Input as the security source or topic to specialize in. It may be a pasted article or reference, or a short phrase such as "prototype pollution in our cache layer" or "GraphQL injection". If it is empty, ask the user what security concern the sub-skill should cover, then stop until they answer. Never invent a topic.
Step 2: Defense-only gate
This command is defense only. If the topic asks for offensive tooling, a working exploit, an attack payload, or detection evasion, refuse and explain that a sub-skill audits and explains, it never produces an attack input. Dual-use content is acceptable only in a clearly defensive framing.
Step 3: Settle the terrain and name, decide create or refine
First settle the terrain: the area the sub-skill covers, never the vulnerability. The area is what the knowledge is about, and the attacks are what it teaches you to defend, so when the topic names an attack, settle on the surface that attack targets. For example, the built-ins set the rule: the regex sub-skill covers ReDoS, yet its terrain is regex, not redos. This same terrain is the title in Step 5 and the tags in Step 6, so name it once here.
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.
- 6d ago First seen · 86 lines · 55 tokens per session scan A c50c37531b97
lagune.specialize is a command published in the GitHub repository wellwelwel/lagune (140 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 1,864 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
update-issue
Update an issue description with structured, evidence-backed content.
new
Plan mode. Generates a plan for a feature based on a description.
next-task
Intelligently determine and prepare the next action based on comprehensive context.
smart-workflow
Execute an intelligent workflow based on current project state and recent commands.
parse-prd
Command "parse-prd" from eyaltoledano/claude-task-master, covering intelligent prd parsing, execution, parsing process, options and post-generation.