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 velinussage/brand-gen --skill brand-gen-orchestrationgit clone --depth 1 https://github.com/velinussage/brand-genWrote 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/velinussage/brand-gen/brand-gen-orchestration)<a href="https://agentmods.dev/skills/velinussage/brand-gen/brand-gen-orchestration"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-orchestration/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/velinussage/brand-gen/brand-gen-orchestration"><img src="https://agentmods.dev/badge/skills/velinussage/brand-gen/brand-gen-orchestration.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 | $0.00182 | $0.08202 |
| Opus 5 | $0.00091 | $0.04101 |
| Sonnet 5 | $0.00036 | $0.01640 |
| Haiku 4.5 | $0.00018 | $0.00820 |
Grade A, and why
brand-gen-orchestration 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 — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand-Gen Orchestration Pipeline
Pi / Sage full-pipeline prompt
For Sage brand work in Pi, use the paste-ready prompt at docs/prompts/pi-sage-brand-gen-full-pipeline.md. It routes Pi through the typed brand_* tools, the brand-orchestrator subagent, exact-text gates, v2/DSPy review, GEPA-ready disagreement fields, and typed mutation loops. Keep this link instead of copying the full prompt into skill bodies.
This skill encodes the 6-phase generation pipeline that produces brand materials through structured preparation, planning, validation, generation, critique, and learning.
Every phase exists for a reason. Preparation prevents repeating mistakes. Planning encodes creative intent. Validation catches contradictions cheaply. Critique enforces a quality bar. Evolution compounds learnings across runs.
Typed runtime (2026-04+, preferred surface)
After the typed-agentic-runtime refactor (Phases 1-6 of the 2026-04 plan), the entire 6-phase pipeline is exposed as typed MCP/CLI tools with structured responses. Pin to these verbs instead of scripting the legacy chain below — the legacy chain is the fallback for CI/scripting, not the primary path.
Architecture docs live in docs/architecture/; GEPA/DSPy optimization and disagreement-record fields are documented in docs/architecture/gepa-dspy-optimization.md, and curated aesthetic capsules are documented in docs/architecture/aesthetic-curation.md, and per-material prompt profiles are documented in docs/architecture/material-prompt-profiles.md.
Orchestration (8 verbs — run the pipeline)
# Convenience: runs all six phases to a natural stop.
bgen orchestrate-material \
--material-type concept-illustration \
--mode hybrid \
--source-version v018 \ # optional: iterate from a prior version
--format json
# Returns: {run_id, stages_completed, stop_reason, next_action, artifacts}
stop_reason enum — branch on this, do not parse narrative phase outputs:
| stop_reason | Meaning | What to do next |
|---|---|---|
approved |
Review accepted. | Report version_id + image_paths. Ask user for a score. |
blocking_findings |
Validate raised blocking issues. | Read artifacts.critique.checks.blocking; fix with typed mutations below; re-run. |
iterating |
Review returned decision: iterate. |
Feed before_after_diffs rows into next run's mutations; re-run with --source-version. |
max_retries |
Orchestrator hit its retry ceiling. | Fall through to per-stage tools to debug. |
needs_user_input |
Ambiguity the orchestrator cannot resolve. | Surface next_action to the user. |
What ships with it
7 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.
- 12d ago First seen · 642 lines · 182 tokens per session scan A 6ea929a67d82
brand-gen-orchestration is a skill published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 182 tokens to every session and 8,202 once invoked, about $0.0009 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…