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 safety-checkgit 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/safety-check)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/safety-check"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/safety-check/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/safety-check"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/safety-check.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 | $0.00059 | $0.00589 |
| Opus 5 | $0.00030 | $0.00295 |
| Sonnet 5 | $0.00012 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
safety-check 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safety Check
Invoke Skill
@safety-check [optional scope]
Examples:
@safety-check@safety-check before publishing@safety-check auth changes
What this skill does
Runs a short risk check before continuing. It is not a full review, not a spec, and not an ADR.
Use it to keep fast work fast while catching obvious reasons to slow down.
Workflow
1. Inspect observable state
Use the available project context:
- current changed files
- recent git diff, if available
- stated task intent
- files touching public contracts, auth, data, secrets, deployment, or infrastructure
- tests or validation already run
Do not invent validation. If tests were not run, say so.
2. Classify risk signals
Flag only signals that are actually present.
| Signal | Examples |
|---|---|
| Contract | API shape, event schema, shared DTO, exported package surface |
| Data | migration, persistence format, irreversible transformation |
| Security | auth, permissions, secrets, input validation, sensitive data |
| Deployment | config, CI/CD, infra, rollout order, runtime compatibility |
| Blast radius | many files, multiple services, cross-layer changes |
| Unknowns | unclear intent, missing acceptance criteria, unverified assumptions |
3. Return a verdict
Use exactly one:
- Go: low risk, reversible, validation path is clear
- Go with caution: risk exists, but a focused check can manage it
- Stop: likely to break users/data/security or the task needs design clarity first
4. Output format
# Safety Check
Verdict: Go | Go with caution | Stop
## Risk Signals
- <Signal>: <specific evidence>
## Must Check Before Continuing
- <Command, file, scenario, or manual check>
## Suggested Path
<Continue in Lite, run @checkpoint, or upgrade to Structured.>
Routing
- If verdict is Go, continue with the current fast path.
- If verdict is Go with caution, run the listed checks before continuing.
- If verdict is Stop, recommend upgrading to Structured and using the relevant skill:
@architectfor design uncertainty@leadfor multi-layer implementation@code-reviewfor completed risky changes
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.
- 11d ago First seen · 97 lines · 59 tokens per session scan A 883922553ef4
safety-check is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 21d ago), licensed MIT. It adds 59 tokens to every session and 589 once invoked, about $0.0003 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
next-action
Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
pull-request-automation
Audits and improves the pull request workflow for a GitHub repository. Covers PR description templates, auto-labelling, CODEOWNERS, PR size checks, and branch protection rules. Invoked when the user asks to improve the PR process, set up PR automation, or add a PR template.
PR Description Writer
Writes clear, thorough pull request descriptions from a diff or list of changes.
agent-code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
andrej-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".