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.
git 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/commands/adonai-labs/agent-runway/fast-lead)<a href="https://agentmods.dev/commands/adonai-labs/agent-runway/fast-lead"><img src="https://agentmods.dev/badge/commands/adonai-labs/agent-runway/fast-lead/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/commands/adonai-labs/agent-runway/fast-lead"><img src="https://agentmods.dev/badge/commands/adonai-labs/agent-runway/fast-lead.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 | $0.00000 | $0.00416 |
| Opus 5 | $0.00000 | $0.00208 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
fast-lead 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 10d 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.
What it actually says
Fast Lead
Read and follow the skill at .cursor/skills/lead/SKILL.md.
Before activating Fast-Track Mode, run escalation signal detection against the task description. Check for any of the following:
| Signal | Condition |
|---|---|
| Contract change | The change modifies a public API, shared interface, or data contract consumed by other components or services |
| Cross-boundary | The change touches more than one bounded context, service, or application layer in a non-trivial way |
| Security surface | The change involves authentication, authorisation, input validation, secrets, or data exposure |
| Data migration | The change requires a schema change or data transformation that cannot be easily rolled back |
| Multi-service coordination | The change requires coordinated deployment or configuration across more than one service |
| Unknown territory | The task description suggests unfamiliarity with the part of the codebase being changed |
If signals are detected, surface them before proceeding:
⚠️ Escalation signals detected:
- [signal name]: [one-line explanation specific to this task]
- [signal name]: [one-line explanation specific to this task]
These suggest this task may be more complex than /fast-lead assumes.
Recommended path: /lead (full workflow)
Continue with /fast-lead anyway? [y/N]
The developer can still proceed — signals are informational, not blocking. If the developer confirms, activate Fast-Track Mode as defined in the skill.
Decision-governance override:
- If risk profile is high impact + hard-to-reverse/irreversible, or uncertainty is high, do not continue in
/fast-lead. - Route to
/leadwith contrarian gate.
Activate Fast-Track Mode as defined in the skill. Collapse Phases 0–2 into a single Fast-Track Validation step. If any risk signal is detected, fall back to the full workflow.
Do not use this for Complex tasks — they always require the full workflow with Phase 0 architect delegation.
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.
- 10d ago First seen · 40 lines · 0 tokens per session scan A 85c85a1124de
fast-lead is a command published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 416 tokens. 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 commands, from other repositories
code-diagram
You are a code analysis expert. Analyze real source code and generate accurate Mermaid diagrams. Never guess or invent — every element must come directly from the code.
arc-audit
Audit a React Native Expo project for mobile UX issues, performance problems, and architecture violations. Use to check code quality against arc-skill best practices. Trigger when the user asks to review code, check for issues, wants a health check, mentions touch targets, accessibility, performance audit, or says 'is…
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.