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-repo-setup)<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-repo-setup"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-repo-setup/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-repo-setup"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/pipeline-repo-setup.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 | $0.00154 | $0.00678 |
| Opus 5 | $0.00077 | $0.00339 |
| Sonnet 5 | $0.00031 | $0.00136 |
| Haiku 4.5 | $0.00015 | $0.00068 |
Grade A, and why
pipeline-repo-setup 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You provision the user's personal pipeline library as a private GitHub repository.
Preconditions
ghCLI is authenticated (assume yes — Daniel has it set up). Ifgh auth statusfails, stop and surface the error.- Confirm the repo name with the user before creating it. Default suggestion:
AI-Video-Pipelines(Train-Case per Daniel's repo naming convention). - Confirm visibility — default private.
What you create
Repo root:
README.md — what's in here, how to consume from a project workspace
CHANGELOG.md — append-only, one entry per pipeline change
reference/
models.md — catalogue of models the user has used + provider + last-known cost
conventions.md — path/parameter conventions shared across pipelines
pipelines/
<pipeline-name>/ — copied from workspace pipelines/ if any exist
SPEC.md
README.md
stages/
run.md
parameters.example.json
templates/
pipeline-spec.md — blank SPEC template
stage.md — blank stage template
.gitignore — node_modules, parameters.json, logs/, runs/, .env
Steps
- Confirm repo name + visibility with the user.
- Create locally at
~/repos/github/my-repos/<Repo-Name>(Daniel's standard base path). Init git. - Scaffold the structure above. Templates for SPEC and stage should mirror what
pipeline-scaffolderandpipeline-builderproduce. - If the current workspace has a
pipelines/directory with content, copy each pipeline intopipelines/in the new repo. Add a CHANGELOG entry per pipeline:Imported from <project> on <YYYY-MM-DD>. - Create the GitHub repo:
gh repo create <name> --private --source . --remote origin --push. - Update the current project's CLAUDE.md (or workspace conventions doc) with a "Pipeline library" section pointing at the new repo.
- Report the repo URL and a 3-bullet summary of what was seeded.
Discipline
- Never create the repo public unless the user explicitly asks.
- Don't overwrite an existing local directory with the same name — stop and ask.
- Commit immediately after scaffolding and after the import; push so the user has remote backup before any further work.
- Don't include
parameters.jsonorruns/— those are per-project and per-run.
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 · 53 lines · 0 tokens per session scan A ab852ac07b52
pipeline-repo-setup is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 154 tokens to every session and 678 once invoked, about $0.0008 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
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
sprint-retrospective
Reconstructs repository history for sprint retrospectives, generating structured markdown with metrics, timelines, and actionable development tips. USE FOR: generate sprint retro document from git history, calculate sprint metrics from PR data, analyze commit timeline patterns. DO NOT USE FOR: planning next sprint…
rollback-agent
Reverts failed fix attempts. Resets git state and posts block comment to issue tracker.
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
issue-manager
Issue lifecycle expert for creating, triaging, and organizing GitHub issues. Use when creating well-formed issues, triaging incoming issues, detecting duplicates, managing relationships (parent/blocking/related), or organizing with labels and milestones.