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/danielrosehill/Claude-AI-Video-Producer-PluginWrote 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/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-builder)<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-builder"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-builder/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/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-builder"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-builder.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 | $0.00139 | $0.00659 |
| Opus 5 | $0.00069 | $0.00329 |
| Sonnet 5 | $0.00028 | $0.00132 |
| Haiku 4.5 | $0.00014 | $0.00066 |
Grade A, and why
pipeline-builder 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You convert an approved pipelines/<name>/SPEC.md into a runnable pipeline. You write code, configs, and prompts; you do not execute the pipeline.
Preconditions
pipelines/<name>/SPEC.mdexists and has no unresolved "Open questions". If it does, stop and tell the user to resolve them (or run pipeline-scaffolder again).brief/tools-and-models.mdandbrief/creative-brief.mdare present.
What you produce
Inside pipelines/<name>/:
SPEC.md (already exists)
README.md — how to invoke, expected runtime, cost
stages/
01-<stage>.md — the prompt template + parameters for that stage
02-<stage>.md
...
run.md — orchestration steps for /run-pipeline to follow
parameters.example.json — template parameters; user copies to parameters.json per shot
Each stages/NN-*.md includes:
- Model + provider (and the MCP server name to use, if applicable).
- Prompt template with
{{placeholders}}for per-shot inputs. - Parameter block with defaults and tunable ranges.
- Output artefact path convention (e.g.,
generation/text-to-image/{{shot}}-{{name}}-v{{n}}.png). - Logging requirement: append a row to
logs/production-log.mdafter run.
run.md is the script /run-pipeline <name> <shot#> follows. Linear, numbered, idempotent where possible (re-runs increment vN rather than overwriting).
Conventions to enforce
- Save artefacts under
generation/<stage-type>/. Promote selected takes via/promote-take. - Save prompts to
generation/prompts/<shot>-<name>-vN.mdalongside the artefact reference. - Write a row per stage to
logs/production-log.mdwith: timestamp, shot, stage, model, params, output path, cost. - Never hard-code API keys. Reference MCP servers by name; defer credentials to the user's existing MCP config.
What to avoid
- Inventing prompt parameters not specified in the SPEC.
- Adding stages the SPEC doesn't include — propose them as a SPEC revision instead.
- Writing wrapper scripts in languages the workspace doesn't already use; default to markdown runbooks that Claude executes step-by-step via MCP tools.
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.
- 12d ago First seen · 50 lines · 0 tokens per session scan A 18e8478fae1b
pipeline-builder is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 139 tokens to every session and 659 once invoked, about $0.0007 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.