Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/adonai-labs/agent-runwaynpx agentmods add skills/adonai-labs/agent-runway/leadWrote 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/lead)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/lead"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/lead.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.05712 |
| Opus 5 | $0.00050 | $0.02856 |
| Sonnet 5 | $0.00020 | $0.01142 |
| Haiku 4.5 | $0.00010 | $0.00571 |
Grade A, and why
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 7d 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Lead
Apply shared policy: ../shared/caveman-skill-engineering.md
Invoke Command
/lead <description of what to build>
Examples:
/lead add order cancellation endpoint/lead refactor payment service to use Result pattern/lead implement background job for invoice generation
Not sure which skill to use? Start with
/start— it classifies intent and routes to the right skill.
Task Classification
Before any phase, classify the task. This determines which phases are required.
Evaluate these three signals:
- Does this involve a design decision? (new pattern, layer boundary, architectural choice)
- Does this touch more than one layer? (e.g. Domain + Application, or Application + API)
- Does this change a contract? (API shape, event schema, public DTO, database migration)
| Classification | Signals | Workflow |
|---|---|---|
| Trivial | All three: No | Skip to Phase 4. Document reason for skipping in a one-line note. |
| Standard | Any one: Yes | Full 10-phase workflow. |
| Complex | Two or more: Yes, or involves a new subsystem or breaking change | Full workflow, Phase 0 mandatory with /architect skill. |
Also classify decision risk for gating depth:
- 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
- contract/public interface change with ambiguous outcomes
- architecture decision with multiple viable paths
Example trivial: fix a typo in a log message, add a missing null guard on an existing method, update a config value. Example standard: add a new query endpoint, extend an existing handler, add a validator. Example complex: introduce a new aggregate, change an event schema, split a service.
Non-Negotiable Decomposition Rule
What ships with it
5 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.
- 7d ago First seen · 529 lines · 100 tokens per session scan A 0db02c21ba1c
lead is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 17d ago), licensed MIT. It adds 100 tokens to every session and 5,712 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
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
design-first
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or…
Architecture Explainer
Reads a codebase or system description and produces a clear, structured architecture overview with diagrams.
explain-codebase
Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.
Brainstorming & Architectural Design
Interactive design process to explore architecture, requirements, and user experience before writing code.
Writing Implementation Plans
Authoring structured, actionable engineering plans before code modifications.