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 skills/ndisisnd/msg/emulatenpx skills add ndisisnd/msg --skill emulategit clone --depth 1 https://github.com/ndisisnd/msgWhat 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 | $0.00170 | $0.01267 |
| Opus 5 | $0.00085 | $0.00633 |
| Sonnet 5 | $0.00034 | $0.00253 |
| Haiku 4.5 | $0.00017 | $0.00127 |
Grade A, and why
emulate 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
emulate
The harness's local run lane. /pre-merge runs the checks and /merge
deploys to a remote target; neither one puts a live app in front of a human on
their own machine. That is this skill's whole job.
/emulate is a leaf: nothing invokes it and it invokes nothing. It has no
place in the intake → plan-pm → plan-em → eng → pre-merge → merge spine and
never blocks it. Run it whenever you want to look at the app.
Dispatch
Every mode runs the same protocol —
refs/protocol.md. The flags only change what Step 0
resolves. First match wins; flags compose.
| Invocation | Also triggers on (natural language) | Effect |
|---|---|---|
/emulate |
"run the app", "open the simulator", "see it running", "show me the app" | Platform resolved from devkit/PLATFORMS.md |
/emulate --ios |
"boot the iOS sim", "run it on iPhone" | iOS lane, PLATFORMS.md not consulted |
/emulate --adr (alias --android) |
"run it on Android", "open the emulator" | Android lane, PLATFORMS.md not consulted |
/emulate --expo |
"start Expo", "run Metro", "expo go" | Pins the runner; the platform still resolves normally |
/emulate --device <name> |
"run it on an iPhone 15 Pro" | Pins the simulator / AVD and skips the device question |
/emulate --dry-run |
"what would this do", "don't actually run it" | Prints the plan and the kill list, launches nothing, kills nothing |
/emulate --help |
— | This table, then stop |
Two axes, not one. --ios and --adr pin the platform — a product
fact, declared in devkit/PLATFORMS.md. --expo pins the runner — a repo
fact, detected from the working tree, because Expo is a toolchain that targets
both platforms rather than a platform of its own. --device is a third,
orthogonal axis. /emulate --expo --ios --device "iPhone 15 Pro" is legal and
means exactly what it reads like.
An unrecognised flag is never ignored. It stops the run with the flag named and the valid set printed — it never falls through to auto-detection.
What ships with it
2 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.
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.
- yesterday First seen · 96 lines · 170 tokens per session scan A e1b7dcc01d69
emulate is a skill published in the GitHub repository ndisisnd/msg (6 stars, last pushed 15d ago), licensed MIT. It adds 170 tokens to every session and 1,267 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
skillspec-migrate
Complete a .agent.partial file by resolving TODO markers.
skill-writer
Review a SkillSpec .agent file for quality, correctness, and adherence to SkillSpec design principles.
skillspec-test
Execute test blocks from a SkillSpec .agent file.
skillspec-backport
Reconcile changes from a modified SKILL.md back into the .agent source file.
split-jvm-nonjvm
Splits a class or several classes in the common source set commonMain into JVM and non-JVM parts into jvmCommonMain and nonJvmCommonMain. This is used to provide some JVM-specific functionality for a class on JVM targets (e.g. Kotlin/JVM or Java backend or Android).
add-java-code-snippets-in-docs
Use when the user asks to add Java tabs/examples to mkdocs docs that already have Kotlin examples (files under docs/docs/.md using === "Kotlin" / Knit INCLUDE+SUFFIX blocks). Handles mkdocs-material tabs, Knit directives, @JavaAPI bridge methods, and JVM factory classes.