ToolYourToolYourAPI Docs

MCP Playbooks

Curated skills and workflows agents can run with run_playbook or solve_task.

Playbooks are markdown skills plus a mapped workflow (or local content path). Prefer run_playbook(skillId) over loading the markdown and inventing steps.

Agent contract

plan_task → solve_task | run_playbook → verify_task

High-value playbooks

Skill idGoal phrasesWorkflow / mode
ship-gateship gate, go live checkship-gate-job
fix-verify-ship-gateverify ship gate after fixship-gate-job + verify_task
fix-verify-security-headersverify headers after fixsecurity-headers-job + verify_task
fix-verify-social-previewverify OG after fixsocial-preview-audit-job + verify_task
fix-verify-core-web-vitalsverify LCP/CLS after fixcore-web-vitals-job + verify_task
fix-verify-seo-auditverify seo after fixfull-seo-audit + verify_task
fix-verify-email-authverify SPF/DKIM after fixemail-auth-security-job + verify_task
frontend-supply-chainSRI, mixed content, CORSfrontend-supply-chain-job
fix-verify-frontend-supply-chainverify supply chain after fixfrontend-supply-chain-job + verify_task
auth-token-hygienedecode jwt, token hygieneauth-token-hygiene-job
developer-ship-checklistbefore deploy, prod readinessdeveloper-ship-checklist-job
seo-site-auditfull seo auditfull-seo-audit
page-performancecore web vitals, LCP/CLScore-web-vitals-job
social-previewopen graph, twitter cardsocial-preview-audit-job
web-security-auditsecurity audit URLfull-security-audit
content-shipship this html, local contentlocal HTML (free unless enhance:true)
dns-email-securitySPF DKIM DMARCemail-auth-security-job
secrets-and-auth-hygienesecret leak scansecrets-hygiene-job

Fix → verify loop

After applying fixes in the harness:

verify_task(goal, { url }, baselinePreviousReport)
# or async
verify_task(goal, input, baseline, async: true) → get_run(runId) → read resultStatus
# or
run_playbook("fix-verify-ship-gate", { url })

Baseline can be a prior solve_task result, verify_task.after, a get_run payload, or a raw jobReport. Prefer verify_task when you still have that baseline — responses are deltas only. Score direction uses metric status (good / needs_improvement / poor), not raw “higher number wins.”

Credits

plan_task estimates credits (heuristic: ~2–3 per tool step). Exact billing matches REST tool costs (1–10 credits).

Docs

On this page