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/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/lead"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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 | $0.00100 | $0.06515 |
| Opus 5.5 | $0.00040 | $0.02606 |
| Sonnet 5.5 | $0.00020 | $0.01303 |
| Haiku 4.5 | $0.00010 | $0.00651 |
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 21d 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 — 591 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.
- 21d ago Changed · +56 lines cb935adf9d7f
- 28d ago Changed · +6 lines 862727fddc45
- 1mo 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 22d ago), licensed MIT. It adds 100 tokens to every session and 6,515 once invoked, about $0.0004 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.
Other skills, from other repositories
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.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…
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.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.