Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wellwelwel/lagunenpx agentmods add skills/wellwelwel/lagune/simulateWrote 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/wellwelwel/lagune/simulate)<a href="https://agentmods.dev/skills/wellwelwel/lagune/simulate"><img src="https://agentmods.dev/badge/skills/wellwelwel/lagune/simulate/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/wellwelwel/lagune/simulate"><img src="https://agentmods.dev/badge/skills/wellwelwel/lagune/simulate.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 | $0.00056 | $0.02677 |
| Opus 5.5 | $0.00022 | $0.01071 |
| Sonnet 5.5 | $0.00011 | $0.00535 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade C, and why
simulate scanned grade C with 1 finding 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 17d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ./temp && mkdir -p ./temp How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulating a Lagune command
This skill exists because simulating a command is deceptively easy to get wrong in a way that wastes the user's time and trust. Hard sessions produced four non-negotiable rules and a method. Follow them exactly.
Use this skill whenever the user asks to "simulate", "demo", "show in practice", "run", or "see in action" any /lagune.* command (charter, detect, plan, harden, verify), or to preview how a command behaves before shipping it.
Before you start (mandatory)
Do not begin a simulation, build a scenario, or copy a fixture until both of these are settled, in this order:
- The user must tell you which Lagune command to simulate. This is required, never assume or pick one. If the user has not named a command (
charter,detect,plan,harden, orverify), ask which one before doing anything else. If they named more than one, confirm the order you will run them in. - Then suggest the fixture, enumerated, and let the user choose. Once the command is known, list the available fixtures (from
.claude/skills/simulate/fixtures/) as a numbered list, each with a one-line description of its scenario, and ask the user to pick one by number. Do not silently default to a fixture. If only one fixture exists, still present it and confirm before using it. If none fits the command, say so and offer to add a new fixture (see the fixtures section).
Only after the command is named and the fixture is chosen do you proceed to the rules and method below.
Why this skill exists (read this first)
A Lagune command is not a standalone program. It is a file of instructions (spec/commands/lagune.<phase>.md, scaffolded as a skill the agent reads) that tells an AI agent how to do a phase of security work. "Running the command" means an agent following those instructions. There is no binary that emits a deterministic result independent of the agent. So a "simulation" is the agent executing the command's steps for real, against a real scenario, while showing its work.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fixtures/image-upload-service/package.json 23 B
- fixtures/image-upload-service/src/lib/fetch-remote.js 459 B runs code
- fixtures/image-upload-service/src/lib/thumbnail.js 311 B runs code
- fixtures/image-upload-service/src/lib/transcode.js 621 B runs code
- fixtures/image-upload-service/src/routes/avatar.js 493 B runs code
- fixtures/image-upload-service/src/routes/import.js 1.6 KB runs code
- fixtures/image-upload-service/src/routes/photos.js 1.4 KB runs code
- fixtures/image-upload-service/src/server.js 3.2 KB runs code
- fixtures/image-upload-service/uploads/.gitkeep 0 B
- fixtures/template-toolkit/bin/cli.js 778 B runs code
- fixtures/template-toolkit/package.json 215 B
- fixtures/template-toolkit/src/index.js 235 B runs code
- fixtures/template-toolkit/src/plugin.js 494 B runs code
- fixtures/template-toolkit/src/plugins/markdown.js 169 B runs code
- fixtures/template-toolkit/src/plugins/slug.js 152 B runs code
- fixtures/template-toolkit/src/remote.js 152 B runs code
- fixtures/template-toolkit/src/render.js 605 B runs code
- fixtures/template-toolkit/src/validate.js 680 B runs code
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.
- 17d ago Changed b0b261ba9021
- 1mo ago First seen · 120 lines · 56 tokens per session scan C 45908b254b65
simulate is a skill published in the GitHub repository wellwelwel/lagune (173 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 2,677 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
octocode-roast
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.
sanity-singletons
Configure singleton documents in a Sanity Studio using the document.singletons registry. Use when a developer wants a fixed-id document (settings, navigation, footer) edited in place, hidden from the default content list, with no "create new" or "duplicate" affordances — or when migrating a userland singleton…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, the App SDK, and Studios…
110-java-maven-best-practices
Use when you need to review, improve, or troubleshoot a Maven pom.xml file — including dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles, or any situation where you want to align your Maven setup with industry best practices. This should…
023-assumption-analysis
Use when a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view needs evaluation, or when a maintainer directly asks to surface hidden…