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 calesthio/generative-media-skills --skill runway-imagegit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/runway-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/runway-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/runway-image/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/calesthio/generative-media-skills/runway-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/runway-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 185 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 30 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 31 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 32 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 33 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 375 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Excessive Agency · line 400 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Excessive Agency · line 453 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00087 | $0.07731 |
| Opus 5 | $0.00044 | $0.03866 |
| Sonnet 5 | $0.00017 | $0.01546 |
| Haiku 4.5 | $0.00009 | $0.00773 |
Grade A, and why
runway-image scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.error import HTTPError, URLError How it starts
The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runway Image
Use the official Runway API to create still images. Prefer Runway-native gen4_image and gen4_image_turbo; keep partner image models explicitly labeled. This skill does not cover Runway video endpoints, the web-app UI, unofficial wrappers, or third-party gateways.
First response
Before writing code or starting a billable task, establish:
- Desired output: subject, environment, composition, style, aspect/resolution, count, and acceptance criteria.
- Mode: text-only generation, reference-guided generation, or a natural-language edit using the source image as a reference.
- References: paths/URLs, rights and consent, each image's role, and whether identity must remain stable.
- Delivery: destination, naming, metadata/manifest, and maximum budget.
- Runtime: direct REST, Python SDK, or Node SDK. Prefer an official SDK for normal application code.
If required creative details are missing, propose a concrete default and ask only the questions that materially change cost, rights, or output. Never make a paid call without explicit approval.
Current contract snapshot
Verified against first-party documentation and the official Python SDK on 2026-07-09. Recheck the API reference, model catalog, pricing, limits, changelog, terms, and usage policy before production deployment; these are volatile.
Routes and authentication
| Purpose | Method and route | Result |
|---|---|---|
| Create an image task | POST https://api.dev.runwayml.com/v1/text_to_image |
{ "id": "..." } |
| Read task | GET https://api.dev.runwayml.com/v1/tasks/{id} |
Discriminated task object |
| Cancel or delete task | DELETE https://api.dev.runwayml.com/v1/tasks/{id} |
Cancels active task or deletes terminal task |
| Start ephemeral upload | POST https://api.dev.runwayml.com/v1/uploads |
Multipart upload instructions plus runwayUri |
Send these headers on API calls:
Authorization: Bearer $RUNWAYML_API_SECRET
Content-Type: application/json
X-Runway-Version: 2024-11-06
What ships with it
1 file 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.
- 9d ago First seen · 531 lines · 87 tokens per session scan A 5bca3dbff7f1
runway-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 7,731 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…