Lagune icon

Lagune

weslley-ara-jo/lagune · v0.21.0 · Agent Skills

by Weslley AraújoScan grade: GoodAwesome AI Plugins

Agent skill collection that secures a project before, during, and after development, in any language or stack: a security charter, the universal skill that hardens code as it is written, and a Blue Team audit that takes each risk from detection to a verified fix

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Lagune a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Agent Skills
  • Claude Code
  • Antigravity CLI
  • Cursor
  • Kimi Code
  • 25 skills
  • Runs hooks on agent events

Before you install

Sign-in
Not declared
Declared access
Interactive, Read, Write
License
Apache-2.0

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • 5 high or critical findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is Lagune?

Lagune is a published agent skills plugin for AI coding agents that works with Agent Skills, Claude Code, Antigravity CLI, Cursor and Kimi Code, developed by Weslley Araújo and distributed through the HOL AI plugin registry. Agent skill collection that secures a project before, during, and after development, in any language or stack: a security charter, the universal skill that hardens code as it is written, and a Blue Team audit that takes each risk from detection to a verified fix.

Canonical slug
weslley-ara-jo/lagune
Version
v0.21.0 · updated Nov 19, 2026

Registry snapshot

Support the project
GitHub Sponsors
Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
25 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

35

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
89/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/wellwelwel/lagune
Source commit
9e8e5e881d41…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Needs review
Security result
89
Security score
5
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-7Hz8mw / cisco-skill-scanner: failedcodex:hol-plugin-scanner-7Hz8mw / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

6/6

5 checks

[claude:.] Code Quality

5/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

6/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

15/15

3 checks

[codex:.] Skill Security

0/5

4 checks

[codex:.] Code Quality

5/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

16/16

6 checks

[gemini:.] Operational Security

6/6

5 checks

[gemini:.] Code Quality

5/10

2 checks

[kimi:.] Kimi Plugin

40/40

10 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

highcode-qualityDANGEROUS_DYNAMIC_EXECUTIONReported 3 times

.claude/skills/simulate/fixtures/template-toolkit/src/render.js: new Function() uses eval() or new Function().

Remove dynamic code evaluation and replace it with explicit control flow.

highskill-securityRISKY_SKILL_INSTRUCTION

The skill includes "curl -sS --max-time 90 'https://registry.modelcontextprotocol.io/v0.1/servers?search=<term>&version=latest&limit=100" and uses curl with uploads, shell composition, or arguments requiring review.

Remove instructions that read sensitive local files, launch shell wrappers, or send workspace data to remote endpoints.

highskill-securityRISKY_SKILL_INSTRUCTION

The skill includes "curl https://cursor.com/install" and uses curl with uploads, shell composition, or arguments requiring review.

Remove instructions that read sensitive local files, launch shell wrappers, or send workspace data to remote endpoints.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the lagune entry from the lagune marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall lagune@lagune.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "lagune",
  "version": "0.21.0",
  "description": "🪼 Your security copilot as you build, your Blue Team when you audit, whether you're a developer or not.",
  "author": {
    "name": "Weslley Araújo",
    "url": "https://github.com/wellwelwel"
  },
  "homepage": "https://lagune.ai",
  "repository": "https://github.com/wellwelwel/lagune",
  "license": "Apache-2.0",
  "keywords": [
    "security",
    "blue-team",
    "sdh",
    "sdd",
    "security-driven-hardening",
    "spec-driven-development",
    "audit",
    "hardening",
    "coding",
    "best-practices",
    "agent-skills"
  ],
  "skills": "./",
  "hooks": {},
  "interface": {
    "displayName": "Lagune",
    "developerName": "Weslley Araújo",
    "shortDescription": "Security-Driven Hardening",
    "longDescription": "Lagune turns a codebase into a more secure one through Security-Driven Hardening, a defensive workflow your agent runs from a spec instead of ad-hoc fixes. It sets the project's security principles, detects what the system actually does (login, file uploads, payments, and so on), plans the fixes that matter for that context, applies them, and verifies that each control holds. Every finding comes in plain language, so developers and non-developers are served alike. Lagune only defends: it audits, hardens, and verifies, and never writes exploits. Its state lives in your project, committed with your code, and its deterministic steps run through the lagune package on npm, which your project can install to run them offline.",
    "category": "Security",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Set this project's security principles.",
      "Detect what this project does and the risks it carries.",
      "Plan the fixes for the risks found in this project."
    ],
    "websiteURL": "https://lagune.ai",
    "privacyPolicyURL": "https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement",
    "termsOfServiceURL": "https://docs.github.com/en/site-policy/github-terms/github-terms-of-service",
    "composerIcon": "./assets/wave.svg",
    "logo": "./assets/logo.png"
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/wellwelwel/lagune
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

25 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • architecture

    .claude/skills/architecture/SKILL.md

    Authoritative record of Lagune's architecture decisions, covering the three owners, what ships, the engine, the skills and plugins, project state, the catalog, the tracking map, and the website's languages. Use when a change depends on one or alters it.

    Raw SKILL.md
  • blind-review

    .claude/skills/blind-review/SKILL.md

    Maps what a branch or the work in progress changes in behavior, before and after, from the code diff alone. Commit messages, documents, and tests stay closed, so the map shows what the code does rather than what anyone says it does. The commits are approved before anything is read.

    Raw SKILL.md
  • calibrate

    .claude/skills/calibrate/SKILL.md

    Confronts every block, warning, and piece of noise a change raises with the false positives real projects trigger, measured on this tree's build, then gives a verdict and the calibration each case needs.

    Raw SKILL.md
  • cdp

    .claude/skills/cdp/SKILL.md

    Visual verification of a running page through Chrome's DevTools Protocol, capturing screenshots and measuring the rendered DOM. Use when a frontend change can only be confirmed once rendered, for layout, spacing, alignment, overflow, or theme tokens.

    Raw SKILL.md
  • dashboard

    .claude/skills/dashboard/SKILL.md

    Authoritative reference for the Lagune dashboard, a live view of a project's .lagune/ chain with a locked-down local action surface. Use before changing anything under src/dashboard/ or src/types/dashboard/.

    Raw SKILL.md
  • engineering

    .claude/skills/engineering/SKILL.md

    Authoritative engineering reference covering code conventions, performance, comments, TypeScript type rules, testing, and commit messages. Use before writing or changing any source file, and when suggesting a commit message.

    Raw SKILL.md
  • ingest

    .claude/skills/ingest/SKILL.md

    Use before reading any .txt file, whatever its name, and whenever a task builds on GitIngest digests. Checks whether a file is a digest (a whole repository in one file) and surveys, searches, and reads it without loading it whole. Returns only the requested lines, with token estimates and anchors for a reusable synthesis.

    Raw SKILL.md
  • mcp-catalog

    .claude/skills/mcp-catalog/SKILL.md

    Find, review, and add MCP servers to the reviewed catalog that lagune.ai serves to Lagune Code. Use when asked to look for servers worth adding, to add a specific server, or to update or drop an entry.

    Raw SKILL.md
  • playground

    .claude/skills/playground/SKILL.md

    Mounts an agent against this tree's build in an isolated home and a fresh fixture, then measures it, probes it, or adds it, before any release publishes that build.

    Raw SKILL.md
  • refine-specialization

    .claude/skills/refine-specialization/SKILL.md

    Refines one built-in specialization to name every attack, bypass, weak guard, and decoy, and to cut what the model already knows, then proves the new text against the old one in blind simulations of detect and verify.

    Raw SKILL.md
  • refine

    .claude/skills/refine/SKILL.md

    Confronts a scope with the engineering, testing, and writer skills, each where it applies, and with the architecture a long-lived project needs, then brings it into line. It removes what should not exist, simplifies, decouples, sharpens responsibilities and names, and places files and directories where they belong. The scope is the unstaged, staged, or current work, commits, a branch, paths, a focus, or the whole workspace, named in any language.

    Raw SKILL.md
  • simulate

    .claude/skills/simulate/SKILL.md

    How to simulate a Lagune command end to end so the user sees both the process and the results in chat. Use when the user asks to simulate, demo, preview, run, or see in action any lagune command. Read this before attempting any such simulation.

    Raw SKILL.md
  • specialize

    .claude/skills/specialize/SKILL.md

    Author a new built-in Lagune specialization inside the Lagune source, not a project's own catalog. Use when adding or refining a security knowledge module that ships with Lagune, against the native layout (`catalog/*.md` plus the built-in index).

    Raw SKILL.md
  • testing

    .claude/skills/testing/SKILL.md

    Authoritative reference for deciding whether a test should exist and what it must assert. Use before writing or changing tests, and when investigating a test failure.

    Raw SKILL.md
  • ui

    .claude/skills/ui/SKILL.md

    Design engineering principles for making interfaces feel polished. Use when building UI, reviewing frontend code, or working on any visual detail, from animations, hover states, shadows, borders, and typography to optical alignment and tabular numbers.

    Raw SKILL.md
  • writer

    .claude/skills/writer/SKILL.md

    Authoritative reference for writing the project's prose. Use before writing, editing, or translating any document, command text, comment, or user-facing message.

    Raw SKILL.md
  • lagune-charter

    skills/lagune-charter/SKILL.md

    Establish or update the project's security charter, the safe-by-default principles every later phase must respect. Reads the project's files to learn what it is and uses, weighs any description you give against them, and asks when something is unclear.

    Raw SKILL.md
  • lagune-detect

    skills/lagune-detect/SKILL.md

    Detect what the system actually does by reading the code, and map the security-relevant findings (login, uploads, payments, data exposure, and so on) with the evidence later phases need. Scans the whole project, named files, or a focused scope.

    Raw SKILL.md
  • lagune-harden

    skills/lagune-harden/SKILL.md

    Apply the defense plan's fixes to the code, safely and one at a time, then record what was applied and what is left. Reads the plan and the charter, then hardens every fix, the fixes, files, or directories you name, or a priority you choose.

    Raw SKILL.md
  • lagune-plan

    skills/lagune-plan/SKILL.md

    Turn what detect found into the defense plan, one fix per finding, each rated by CVSS v4.0 (category, CVSS, priority) and tied to a charter principle. Reads the detect map and the charter, then plans every finding, named paths, or a concern you describe.

    Raw SKILL.md
  • lagune-prove

    skills/lagune-prove/SKILL.md

    Prove detected findings with runnable, defense-only evidence. For each finding the detect map carries, it writes a safe-path JavaScript test and a self-contained advisory under `.lagune/proofs/`. The test asserts secure behavior, never an exploit.

    Raw SKILL.md
  • lagune-repair

    skills/lagune-repair/SKILL.md

    Repair Lagune's internal tracking so each item stays whole when files are renamed or moved, and check every memory artifact against its template. A maintenance pass, not a security phase, rewriting the tracking map across all phases in one pass.

    Raw SKILL.md
  • lagune-specialize

    skills/lagune-specialize/SKILL.md

    Specialize Lagune from a source or topic you give it, distilling it into a new on-demand specialization the detect and verify phases load later. It writes a focused, language-agnostic, defense-only knowledge module, never an exploit.

    Raw SKILL.md
  • lagune-verify

    skills/lagune-verify/SKILL.md

    Prove each applied control holds by confronting the hardening record with the code, writing each verdict back into that record, then standing the findings proven closed out of the chain. Read-only on your code, it writes only Lagune's own chain.

    Raw SKILL.md
  • lagune

    skills/lagune/SKILL.md

    Use this skill whenever you are about to build or change code. It builds safe-by-default from the project's charter and the defensive security knowledge the work touches, then checks the result.

    Raw SKILL.md

File inventory

.agents/plugins/marketplace.json

file

336 bytes

0097dcf12b367026…

.claude-plugin/marketplace.json

file

806 bytes

0318e16d2f93778c…

.claude-plugin/plugin.json

file

640 bytes

f9043e25af30e408…

.claude/skills/architecture/SKILL.md

skill

17,523 bytes

68810e883621197b…

.claude/skills/blind-review/SKILL.md

skill

7,810 bytes

ecf74ebe6b6368e9…

.claude/skills/blind-review/tools/blind-diff.sh

file

8,889 bytes

eb7b327a8b4f04a5…

.claude/skills/calibrate/SKILL.md

skill

6,330 bytes

ce66615db6995292…

.claude/skills/cdp/SKILL.md

skill

2,995 bytes

e182475a74b09efe…

.claude/skills/cdp/tools/cdp.ts

file

6,474 bytes

691b63a462d41d6d…

.claude/skills/dashboard/SKILL.md

skill

12,601 bytes

f376101bbd160544…

.claude/skills/engineering/SKILL.md

skill

8,176 bytes

3f7626634ab95d91…

.claude/skills/ingest/SKILL.md

skill

4,684 bytes

63c2268e6091b265…

.claude/skills/ingest/tools/anchor.ts

file

696 bytes

ec8be9659e7c4507…

.claude/skills/ingest/tools/commands/anchors.ts

file

1,647 bytes

e157201e9f46f314…

.claude/skills/ingest/tools/commands/extract.ts

file

2,656 bytes

19734ca0ff7f617a…

.claude/skills/ingest/tools/commands/files.ts

file

1,100 bytes

4cc5797a0cc74180…

.claude/skills/ingest/tools/commands/is.ts

file

600 bytes

286e8aaa8f21778c…

.claude/skills/ingest/tools/commands/outline.ts

file

3,181 bytes

901861c4f3ee1407…

.claude/skills/ingest/tools/commands/overview.ts

file

3,629 bytes

328470cddccbc427…

.claude/skills/ingest/tools/commands/read.ts

file

1,589 bytes

8d33f4faf3985d53…

.claude/skills/ingest/tools/commands/search.ts

file

3,693 bytes

8ddae2644806bf51…

.claude/skills/ingest/tools/commands/tree.ts

file

2,298 bytes

33cf642bf95af618…

.claude/skills/ingest/tools/digest.ts

file

4,465 bytes

916f62df5a1cda16…

.claude/skills/ingest/tools/fail.ts

file

81 bytes

d51c5156825cc926…

.claude/skills/ingest/tools/format.ts

file

798 bytes

4bcc727e32e25c05…

.claude/skills/ingest/tools/hidden.ts

file

474 bytes

073e5dd2d2f08d91…

.claude/skills/ingest/tools/ingest.ts

file

5,921 bytes

050dd7ef9d52df39…

.claude/skills/ingest/tools/package.json

file

23 bytes

3ca9d4afd2142508…

.claude/skills/ingest/tools/paths.ts

file

433 bytes

fb124db35be77fa4…

.claude/skills/ingest/tools/pattern/check.ts

file

1,796 bytes

d568f62fe379648d…

.claude/skills/ingest/tools/pattern/match.ts

file

1,323 bytes

f2b1aa9152fd42f5…

.claude/skills/ingest/tools/pattern/worker.ts

file

491 bytes

12d5b83f3a28b788…

.claude/skills/ingest/tools/selection.ts

file

2,261 bytes

0df195f2d50695cf…

.claude/skills/ingest/tools/stats.ts

file

567 bytes

74a557bebacc26cb…

.claude/skills/ingest/tools/types.ts

file

1,720 bytes

94e96b8c17347030…

.claude/skills/mcp-catalog/SKILL.md

skill

13,088 bytes

8e7b497d49436877…

.claude/skills/playground/SKILL.md

skill

12,255 bytes

0a86910de655b932…

.claude/skills/refine-specialization/simulation.md

file

7,624 bytes

0731f32093c5b09c…

.claude/skills/refine-specialization/SKILL.md

skill

6,924 bytes

5b9e6c6dcb79c3c4…

.claude/skills/refine/SKILL.md

skill

9,567 bytes

c68c93c363dfe04b…

.claude/skills/simulate/fixtures/image-upload-service/package.json

file

23 bytes

3ca9d4afd2142508…

.claude/skills/simulate/fixtures/image-upload-service/src/lib/fetch-remote.js

file

459 bytes

2a164b3f40211858…

.claude/skills/simulate/fixtures/image-upload-service/src/lib/thumbnail.js

file

311 bytes

809643b024cdc052…

.claude/skills/simulate/fixtures/image-upload-service/src/lib/transcode.js

file

621 bytes

5af0b1518ce4e73f…

.claude/skills/simulate/fixtures/image-upload-service/src/routes/avatar.js

file

493 bytes

f166a4ec8ab174f4…

.claude/skills/simulate/fixtures/image-upload-service/src/routes/import.js

file

1,606 bytes

c9aaa9f0a227bbff…

.claude/skills/simulate/fixtures/image-upload-service/src/routes/photos.js

file

1,464 bytes

949896929a76987a…

.claude/skills/simulate/fixtures/image-upload-service/src/server.js

file

3,321 bytes

2ddf04c5c4e74e7e…

.claude/skills/simulate/fixtures/template-toolkit/bin/cli.js

file

778 bytes

9d7238e1bb184c33…

.claude/skills/simulate/fixtures/template-toolkit/package.json

file

215 bytes

e01c9d013ccc5a56…

.claude/skills/simulate/fixtures/template-toolkit/src/index.js

file

235 bytes

7cbb283a841afbb6…

.claude/skills/simulate/fixtures/template-toolkit/src/plugin.js

file

494 bytes

d5b7d1c16c967a22…

.claude/skills/simulate/fixtures/template-toolkit/src/plugins/markdown.js

file

169 bytes

71383bb273b6de38…

.claude/skills/simulate/fixtures/template-toolkit/src/plugins/slug.js

file

152 bytes

dec28fbe808a16ad…

.claude/skills/simulate/fixtures/template-toolkit/src/remote.js

file

152 bytes

c6c795481555a130…

.claude/skills/simulate/fixtures/template-toolkit/src/render.js

file

605 bytes

fb32237cf0719ebd…

.claude/skills/simulate/fixtures/template-toolkit/src/validate.js

file

680 bytes

c20cb65dffaefbde…

.claude/skills/simulate/SKILL.md

skill

12,126 bytes

28e9666f93afe8b2…

.claude/skills/specialize/SKILL.md

skill

6,409 bytes

794f2215a344ed8d…

.claude/skills/testing/SKILL.md

skill

4,634 bytes

90d11c30a48c2801…

.claude/skills/ui/animations.md

file

10,554 bytes

adf5847d4ff64a6f…

.claude/skills/ui/performance.md

file

3,257 bytes

4b47ffc5d3fa48a7…

.claude/skills/ui/SKILL.md

skill

10,115 bytes

3466cf8aa4794548…

.claude/skills/ui/surfaces.md

file

6,032 bytes

8dc24875eb93f248…

.claude/skills/ui/typography.md

file

4,104 bytes

4c9bfbdef845596b…

.claude/skills/writer/SKILL.md

skill

4,343 bytes

e9b19becce4f75ea…

.codex-plugin/plugin.json

plugin-manifest

1,995 bytes

5dc8d4804e984b8c…

.cursor-plugin/marketplace.json

file

405 bytes

388d2b268370cd9b…

.cursor-plugin/plugin.json

file

621 bytes

730cbc1cd62cfa24…

.github/dependabot.yml

file

795 bytes

0ef909cd335c693c…

.kimi-plugin/plugin.json

file

1,008 bytes

ce2b5b47a2c9c48b…

assets/logo.png

asset

31,456 bytes

39d135cc057bcbf1…

assets/wave.svg

asset

1,721 bytes

39245357e0188d8a…

CLAUDE.md

file

14,212 bytes

bc5f40eadcdc17c1…

gemini-extension.json

file

198 bytes

9475038423b3e384…

LICENSE

file

15,152 bytes

ef7f96b62eadeed0…

package-lock.json

file

355,754 bytes

0ec5d9e0e6395bd6…

package.json

file

3,945 bytes

54047d8f87889675…

README.md

file

17,546 bytes

a6549ae161e4658d…

SECURITY.md

file

1,974 bytes

1c829a54c8e9939c…

skills/lagune-charter/SKILL.md

skill

12,474 bytes

3e89a976ba7cc5a9…

skills/lagune-charter/template.md

skill

3,552 bytes

0816120572e46de2…

skills/lagune-detect/SKILL.md

skill

14,084 bytes

d64fd5f3c7caf91b…

skills/lagune-detect/template.md

skill

3,929 bytes

0b4179225bbeec8a…

skills/lagune-harden/SKILL.md

skill

15,801 bytes

b2fd0fc42c9ce9b8…

skills/lagune-harden/template.md

skill

4,073 bytes

3bb1d2336bf83964…

skills/lagune-plan/SKILL.md

skill

16,029 bytes

6ffee8c171b64ac5…

skills/lagune-plan/template.md

skill

9,420 bytes

962bd7f32e871fc0…

skills/lagune-prove/agents/openai.yaml

skill

43 bytes

a1499d95abd84475…

skills/lagune-prove/SKILL.md

skill

18,158 bytes

66e863ebf1a5b5aa…

skills/lagune-prove/template.md

skill

9,028 bytes

f243cacf28d07187…

skills/lagune-repair/SKILL.md

skill

7,278 bytes

58344bd7da1c4c08…

skills/lagune-specialize/agents/openai.yaml

skill

43 bytes

a1499d95abd84475…

skills/lagune-specialize/SKILL.md

skill

8,559 bytes

a0e4918cb6a29429…

skills/lagune-specialize/template.md

skill

6,237 bytes

224e70f6626feb1a…

skills/lagune-verify/SKILL.md

skill

14,615 bytes

536924bea752b3bd…

skills/lagune/SKILL.md

skill

6,670 bytes

6345ccd07cb884e4…

tsconfig.json

file

903 bytes

6d9d9a7bba6c3703…

Lagune — Frequently asked questions

What is Lagune?
Lagune is an AI plugin in the HOL registry. Agent skill collection that secures a project before, during, and after development, in any language or stack: a security charter, the universal skill that hardens code as it is written, and a Blue Team audit that takes each risk from detection to a verified fix.
How do I install Lagune?
Install Lagune in your harness: Claude Code — /plugin marketplace add wellwelwel/lagune; Cursor — npx [email protected] add wellwelwel/lagune; Antigravity CLI — npx [email protected] add wellwelwel/lagune. Full step-by-step guidance is on the HOL plugin page.
How do I install Lagune in HOL Guard?
To install Lagune in HOL Guard, start with hol-guard plugin install weslley-ara-jo/lagune --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Lagune in Claude Code?
To install Lagune in Claude Code, start with /plugin marketplace add wellwelwel/lagune. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Lagune in Cursor?
To install Lagune in Cursor, start with npx [email protected] add wellwelwel/lagune. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How is the Trust Score for Lagune computed?
Lagune has a HOL Trust Score of 35 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/weslley-ara-jo%2Flagune/trust
Who publishes Lagune?
Lagune is published by Weslley Araújo and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins