Borrowing it
Nothing to install: this file belongs to alecs5am/ralphy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alecs5am/ralphy/main/.agents/skills/producer/SKILL.mdgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/producer)<a href="https://agentmods.dev/skills/alecs5am/ralphy/producer"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/producer/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/alecs5am/ralphy/producer"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/producer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 135 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00164 | $0.04548 |
| Opus 5 | $0.00082 | $0.02274 |
| Sonnet 5 | $0.00033 | $0.00910 |
| Haiku 4.5 | $0.00016 | $0.00455 |
Grade A, and why
producer 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 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.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Producer playbook
Canonical flow lives in the contract. The producer is the end-to-end WRAPPER that drives the agent production contract across roles — it does not define its own divergent sequence. The full chat-request-to-packaged-Unit path (every phase + its required artifact + stop conditions + cheap-vs-native validation + the resume model) is the canonical Unit lifecycle; the contract owns the phase order (intake → … → render → eval → repair → unit → postmortem) and the per-phase artifacts; this playbook owns the orchestration (when to batch, when to extract a template, cost rollup, ETA gating). Self-check progress with
ralphy project status <id> --contract(alias--lifecycle). If this file and the contract disagree on order, the contract wins.
Positioning. Chat is the user interface; the Ralphy CLI is the agent runtime. The user asks for the end-to-end result in chat — YOU sequence the
ralphyverbs below on their behalf. Never hand the user a batch script to run themselves.
Read this when: "make video end-to-end", "make N videos", "run full pipeline", batch generate, "save as template", "create template from", "review batch", "content farm", "make 20 videos / 20 posts / an ad pack batch for X" (farm mode, see below).
Nothing-to-final-video role. Sequences other roles (researcher → scenarist → art-director → editor), decides when to batch, when to extract a template, when to do a smoke pass, and how to roll up state across N projects. Also handles batch review and cost rollup.
STOP rule. Producer never writes scenarios / prompts / composition code, and never runs a batch loop by hand — every step is a
ralphy template use/ralphy batch createinvocation. AGENTS invariant #2.
Research-bootstrap-before-the-plan (#416). After the template match and BEFORE
ralphy project plan, run the research bootstrap:chooseResearchDepth({ brief, contentMode, unitCount })(cli/lib/research-bootstrap.ts) decidesnone/quick/deep, then route the depth to the EXISTING surface —quick→ site-grounding sub-agent (AGENTS #15) / a fewralphy ref pull;deep→ralphy research run+ralphy research scrape-profile. A batch (N≥3) almost always lands ondeep(themulti-unit-farmtrigger), and the deep scan amortizes across the whole batch. Distill the result intoartifacts/refs/research-facts.json(ProductBrandFacts,cli/lib/schemas/research-facts.ts) and set the plan'sbenchmarkSourceto cite it. Full discipline:research-bootstrap.md. No new crawler — reuse the research engine + site-grounding.
Plan-as-source-of-truth (#407). After the template match (and the research bootstrap above) and before scenario work, write the plan with
ralphy project plan <id> --brief "<text>"(contract phase 7). Downstream roles — scenarist, art-director, editor, evaluator — READ<project>/production-plan.json(target language, aspect/platform, content mode, format + template, register, scene count / duration, model stack, cost estimate, first checkpoint,benchmarkSource) rather than relying only on chat memory; this is what lets a role resume after a context reset. Re-running the verb auto-versions the prior plan (.v1), never overwrites it.
What ships with it
3 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.
- 9d ago First seen · 144 lines · 164 tokens per session scan A 9d05f209eceb
producer is a skill published in the GitHub repository alecs5am/ralphy (132 stars, last pushed 14d ago), licensed Apache-2.0. It adds 164 tokens to every session and 4,548 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 2026-08-30.
Other skills, from other repositories
molecule-visualization
Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.