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/yonatangross/orchestkitnpx agentmods add skills/yonatangross/orchestkit/emulate-seedWrote 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/yonatangross/orchestkit/emulate-seed)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/emulate-seed"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/emulate-seed/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/yonatangross/orchestkit/emulate-seed"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/emulate-seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 107 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 89 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 92 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 95 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 298 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 350 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 351 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 352 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 353 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00086 | $0.04706 |
| Opus 5.5 | $0.00034 | $0.01882 |
| Sonnet 5.5 | $0.00017 | $0.00941 |
| Haiku 4.5 | $0.00009 | $0.00471 |
Grade A, and why
emulate-seed 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 21d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream version reference: emulate 0.12.0 (2026-09-30).
Emulate Seed Configs
Generate and manage seed configs for emulate (Apache-2.0) — Vercel Labs' stateful API emulation tool. Each category has individual rule files in rules/ loaded on-demand.
Paired agent: This skill pairs with the
emulate-engineersubagent (subagent_type: "ork:emulate-engineer"). When a task involves generating a full emulate config from scratch, webhook HMAC setup, CI pipeline integration, or parallel-worker port isolation, spawn the agent rather than handling it inline — it has the full 13-emulator service-port matrix and seed-rules in context.
Not mocks. Emulate provides full state machines with cascading deletes, cursor pagination, webhook delivery, and HMAC signature verification. Create a PR via the API and it appears in GET /repos/:owner/:repo/pulls. Delete a repo and its issues, PRs, and webhooks cascade-delete.
New in 2026-04 (emulate 0.4.x)
- Modular
@emulators/*packages — each service is its own package (@emulators/github,@emulators/stripe, etc.); top-levelemulatere-exportscreateEmulatorand the CLI. - 4 new services (12 total):
mongoatlas:4007,okta:4008,resend:4009,stripe:4010with drop-in seed YAML blocks. - Resend local inbox —
GET http://localhost:4009/inboxreturns captured emails for assertions without hitting a real provider. - Stripe hosted checkout — real session redirect flow +
checkout.session.completed/expiredwebhook delivery, suitable for E2E payment tests. - MongoDB Atlas — Admin API v2 (projects/clusters/DB users) + Data API v1 with full CRUD + aggregate.
- Okta OIDC — full discovery, JWKS,
authorize/token/userinfo/revoke/introspectplus Users/Groups/Apps CRUD. - Entra / Apple / Slack expansions (v0.4.0) — PKCE + refresh rotation (Entra), RS256 JWKS (Apple), OAuth v2 consent UI (Slack).
@emulators/adapter-next— catch-all Next.js route handler runs emulators on the same origin as the app; fixes OAuth callback URL drift on Vercel preview deploys.
What ships with it
17 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.
- references/api-coverage.md 5.4 KB
- references/cli-reference.md 2.2 KB
- references/dep-to-emulator-map.json 2.3 KB
- references/ork-delta.md 3.3 KB
- references/upstream-github.md 18 KB
- references/upstream-google.md 19 KB
- references/upstream-vercel.md 15 KB
- references/upstream.md 12 KB
- rules/_sections.md 1.3 KB
- rules/_template.md 339 B
- rules/auth-tokens.md 3.1 KB
- rules/parallel-ci.md 3.3 KB
- rules/seed-config.md 2.5 KB
- rules/service-selection.md 2.6 KB
- rules/webhook-setup.md 2.8 KB
- scripts/auto-discover.sh 4.1 KB runs code
- test-cases.json 3.4 KB
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.
- 21d ago Changed · +2 lines 52334dbc0c26
- 23d ago Changed · -1 lines e613c9181f14
- 28d ago Changed · -1 lines 3e4aecbef236
- 1mo ago Changed 555b5fbf9a64
- 1mo ago Changed dab0a20de4c5
- 1mo ago First seen · 375 lines · 86 tokens per session scan A a349205bca51
emulate-seed is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 4,706 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
jira-validate-production
Check that the fix a Jira issue carries is live on the PRODUCTION site and behaves as the issue asked, then close the card, or open a follow-up issue for what failed. Insert into the prompt of a run started on a batch of merged issues, or of a Jira post-deploy column rule.
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…
system-tests
Generic, composable conventions for system tests — black-box tests exercising the running system from the outside through its public surface. Defines the stack-neutral contract (no internals, environment coordinates as configuration, test isolation, total verdict reporting) and the taxonomy of expectation origins…