🎓 Teach Lagune a new specialization, from a source or topic you give it.
It reads the material and distills it into a focused, defense-only specialization, shaped exactly like the built-in ones, so the detect and verify phases load it afterwards like any other. It only audits and explains: it never writes attack inputs or exploits, and it never touches your code.
- From an article
- From an exploit
- From a topic
# A link or reference: Lagune distills it into the defense
/lagune-specialize https://owasp.org/www-community/attacks/SQL_Injection
# An attack as the source: the specialization is still the defense
/lagune-specialize "' OR 1=1 -- splices SQL into the query text"
# Or just name what to cover
/lagune-specialize SQL injection
Pointing it at an attack is fine when the goal is to defend against it: an exploit write-up is study material it distills into the defense. The specialization it produces always audits and explains, it never produces a working exploit, payload, or evasion.
What it writes
The result is two files in your project, committed and reviewable alongside your code:
- The specialization at
.lagune/catalog/<name>.md, shaped like the built-in ones. - Its entry in
.lagune/configs.json, where your project indexes its own specializations for the catalog to merge with the built-ins.
It then lists the catalog to confirm the new entry is there. Your own specializations are always in the catalog, whatever its categories. You never add a command or touch the package: a new specialty is one knowledge file plus one index entry, written into your own project.
Refine, never overwrite
Specializing a name that already exists, whether a built-in like regex or one you specialized before, reconciles the current file instead of replacing it. It reads what is there, folds the new knowledge in, keeps what still holds, and rewrites what changed. Nothing is discarded unseen. A specialization of yours shadows a built-in of the same name, so you can sharpen a built-in for your own project without losing it.
- The new specialization loads exactly like a built-in: the detect and verify phases pick it up on demand, or load it yourself with
npx lagune read catalog <name>and give it a task. - When the material has an identifiable origin (an article, an author, a link, a standard), the specialization credits it. A bare topic carries no source.
It runs only when you call it: the agent never starts it on its own.
Frequently Asked Questions
Run /lagune-specialize with a source or topic. It distills it into a defense-only specialization, written to .lagune/catalog/<name>.md plus its entry in .lagune/configs.json.
Yes, as a source, never as output. An attack can be the source, never the product. Specialize never writes attack inputs or exploits.
No. It refines, never overwrites.
