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 adonai-labs/agent-runway --skill startgit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/start)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/start"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/start/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/adonai-labs/agent-runway/start"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/start.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 | $0.00090 | $0.02362 |
| Opus 5 | $0.00045 | $0.01181 |
| Sonnet 5 | $0.00018 | $0.00472 |
| Haiku 4.5 | $0.00009 | $0.00236 |
Grade A, and why
start 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 8d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start
Invoke Command
/start <description of what you want to do>
Examples:
/start I need to add email notifications when an order is placed/start there's a bug where users can see other users' orders/start we need to provision a new Azure Service Bus namespace/start the payment service is getting too complex, it needs cleaning up/start PROJ-501
Not sure if this is the right skill? It always is —
/startfigures out where to go from here.
What this skill does
Takes any description of work — vague, technical, ticket-based, or in plain language — and produces:
- A clear classification of what kind of work this is
- The right skill to use and why
- Relevant project context pre-loaded for that skill
- A ready-to-go handoff so the developer can proceed immediately
Workflow — 3 Phases
Phase 1 — Understand the intent
Read the developer's description carefully. Identify the primary intent:
| Intent signal | Likely category |
|---|---|
| "add", "build", "implement", "create", "new endpoint/feature" | Implementation |
| "autonomous", "without supervision", "run unattended", "low supervision" | Autonomous implementation |
| "fix", "broken", "not working", "bug", "error", "wrong behaviour" | Bug fix |
| "review", "check this", "audit", "PR review" | Code review |
| "checkpoint", "save state", "handoff", "pause here", "resume later" | Checkpoint |
| "safety check", "risk check", "is this safe", "before I continue" | Safety check |
| "clean up", "refactor", "simplify", "too complex", "hard to read" | Refactor |
| "infrastructure", "provision", "Bicep", "Terraform", "Azure resource" | IaC |
| "design", "should I use", "trade-off", "architecture decision", "ADR" | Architecture |
| "validate", "is this ticket ready", "check this story" | Ticket validation |
| "product-ready", "PO review", "business readiness", "evaluate this spec as PO" | PO evaluation |
Jira ticket key (e.g. PROJ-123) or path to .md file |
Ticket validation → then re-classify |
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.
- 8d ago First seen · 257 lines · 90 tokens per session scan A e2fbdd0daf4f
start is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 18d ago), licensed MIT. It adds 90 tokens to every session and 2,362 once invoked, about $0.0005 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
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
full-audit
Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.