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 iacgit 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/iac)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/iac"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/iac/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/iac"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/iac.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 | $0.00120 | $0.01657 |
| Opus 5.5 | $0.00048 | $0.00663 |
| Sonnet 5.5 | $0.00024 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
iac 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure as Code
Invoke Command
/iac <what you need>
Examples:
/iac new container service + managed Postgres for the orders service/iac review infra/main.tf/iac add a secrets store and reference it from app settings/iac create dev and prod parameter files
Provider and tool are detected from the repository (*.tf, *.bicep, template.yaml/cdk.json, Pulumi.yaml) or asked once. Examples in standards.md and reference.md show Azure/Bicep alongside AWS and GCP equivalents; apply the same principles to whichever provider is in use.
Not sure which skill to use? Start with
/start- it classifies intent and routes to the right skill.
Workflow
Follow these steps in order.
Step 0 - Risk Classification and Routing Gate
Before any IaC change, classify:
- Impact: low/medium/high
- Reversibility: reversible/hard-to-reverse/irreversible
- Uncertainty: low/medium/high
- Cost of error: low/medium/high
Contrarian trigger (any true):
- impact is high and reversibility is hard-to-reverse or irreversible
- uncertainty is high
- migration/cutover with ambiguous rollback
- architecture decision with multiple viable infrastructure patterns
Execution mode:
- Execution-only: low risk + reversible + low uncertainty
- Execution+validation: medium risk or multi-resource change
- Execution+contrarian: contrarian trigger active
Policy:
- Execution-only: continue with minimal questions and minimal process overhead.
- Execution+validation: continue with normal IaC workflow.
- Execution+contrarian: run mandatory contrarian review before writing IaC.
Decision action table:
| Profile | Action |
|---|---|
| High impact + irreversible + high uncertainty | Block - stop and escalate before changes |
| Medium risk profile | Warn - continue only with explicit risk notes and validation checks |
| Low risk + reversible + low uncertainty | Execute - use short path |
Step 0.5 - Contrarian Review (Required when triggered)
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 Changed · -1 lines · +30 tokens per session 25d3efb12d36
- 2mo ago First seen · 187 lines · 90 tokens per session scan A 6d880a453d3a
iac is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 1,657 once invoked, about $0.0005 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 2026-08-31.
iac compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| iacadonai-labs/agent-runway | Skill | 2 | 2d ago | MIT | A | 120 | Claude Code, Codex |
| doubt-driven-developmentaddyosmani/agent-skills | Skill | 114k | 5d ago | MIT | A | 96 | Claude Code |
| code-changesJanDeDobbeleer/oh-my-posh | Skill | 24k | 2d ago | MIT | A | 48 | Claude Code, Codex |
| systemic-issue-triageGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 57 | Claude Code, Codex |
| issue-root-resolutionGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 45 | Claude Code, Codex |
| rdd-defect-workflowGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 41 | Claude Code, Codex |
| project-checkAlexZio00/sovereign-skills | Skill | 151 | 2d ago | MIT | A | 81 | Claude Code, Codex |