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 skills add stunt-double/stuntdouble-mcp --skill setup-guardrailsgit clone --depth 1 https://github.com/stunt-double/stuntdouble-mcpWrote 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/stunt-double/stuntdouble-mcp/setup-guardrails)<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/setup-guardrails"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/setup-guardrails/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/stunt-double/stuntdouble-mcp/setup-guardrails"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/setup-guardrails.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 | $0.00047 | $0.00890 |
| Opus 5 | $0.00023 | $0.00445 |
| Sonnet 5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
setup-guardrails 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up guardrails
When to use
- A flow is business-critical (signup, sign-in, checkout, password reset) and must not silently break
- You want regressions caught on every deploy or on a schedule, not by customers
- You already verified a change (see
verify-change) and want to keep that coverage standing
Instructions
-
Resolve context:
list_workspaces()→ pick the workspacelist_projects(workspace_id)→ match the product URL to a project, or letcreate_checklistfind/create it
-
Ensure an actor exists:
list_actors(workspace_id), elsecreate_actor(...)
-
One checklist per flow:
create_checklist(...)per critical flow, each with focused instructions and 3–6 crisp pass/fail checks- Small, focused checklists give clearer failure signals than one giant checklist
-
Record any standard the flows are held to:
list_project_guidelines(project_id)to read what the project is already held to, thenadd_project_guideline(...)for anything missing- A guideline reaches every run, review and interview for the project, so the checks can assert it instead of restating it in each checklist
-
Confirm a green baseline before automating:
run_checklist(checklist_id)for each, pollget_checklist_run(run_id)until terminal- Fix flaky checks now — a noisy guardrail gets ignored
-
Automate re-runs with a workflow:
create_workflow(...)with a trigger:schedulewith a cron (daily is a good default), passing{ cron, timezone }intrigger_configusing the timezone fromget_meso the hour means the user's hour, or- event triggers (
vercel_event,github_event) to run on deploys and pull requests when those connections are configured in the workspace
add_workflow_step(...)— onerun_checkliststep per checklist, plus anotificationstep so failures reach the teamtoggle_workflow(workflow_id)to activate
-
Confirm coverage to the user:
- What is covered, when it runs, where failures are reported, and how to extend it (add a checklist, then add a step)
- Manage everything later at app.stuntdouble.io
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.
- 9d ago First seen · 73 lines · 47 tokens per session scan A f8b309fb0477
setup-guardrails is a skill published in the GitHub repository stunt-double/stuntdouble-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 47 tokens to every session and 890 once invoked, about $0.0002 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
Checkly Monitoring as Code
Teach agents to build synthetic monitoring as code with Checkly, including Playwright browser checks, API checks, alerting, and CI deploy workflows.
CI Test Sharding Parallelization
Teach agents to shard and parallelize Playwright, Jest, and pytest suites in CI to reduce wall-clock time while merging reports reliably.
CI/CD Pipeline Config
CI/CD pipeline configuration skill for test automation, covering GitHub Actions, Jenkins, GitLab CI, test parallelization, reporting, and artifact management.
e2e-failure-paths
Validate pipeline behavior under failure conditions. Use when simulating test failures, SAST failures, build failures, validating no GitOps update occurs, or checking error propagation.
e2e-happy-path
Validate the full pipeline success path from commit to deployment. Use when triggering a full CI pipeline run, validating build artifacts, GitOps update, reconciliation, deployment, or running smoke tests.
Ephemeral Environment Testing
Testing in ephemeral preview environments for pull requests including environment provisioning, data seeding, and automated teardown.