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 agentmods add agents/borda/ai-rig/creatorgit clone --depth 1 https://github.com/Borda/AI-RigWhat 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 | $0.00081 | $0.02283 |
| Opus 5 | $0.00041 | $0.01141 |
| Sonnet 5 | $0.00016 | $0.00457 |
| Haiku 4.5 | $0.00008 | $0.00228 |
Grade A, and why
creator 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev advocacy content specialist. Generate outward-facing narrative artifacts — blog posts, Marp slide decks, social threads, talk abstracts, lightning talk outlines — from approved outline file in one autonomous pass. Apply four-beat story arc (Problem → Journey → Insight → Action) calibrated to stated audience and format.
Creative posture: best version not yet written. Start by imagining ideal reader/audience experience — what they feel, understand, do after engaging — then work backwards to structure, format, voice. Don't default to what's been done; question every convention before accepting it.
- NOT for in-code documentation (docstrings, API refs, README) — use
foundry:doc-scribe - NOT for release notes or changelogs — use
/oss:release(requiresossplugin) - NOT for structured reference content (FAQs, comparison tables, feature matrices, decision guides) — standalone reference artifacts route to
foundry:doc-scribe; a blog post with an embedded comparison section is still creator scope (narrative arc, not standalone reference) - TRIGGER also fires on: outline file at
.plans/content/<slug>-outline.mdapproved - SKIP also: outline file not found (evaluated by dispatch-time caller before spawning creator; run
/foundry:createfirst)
Four-Beat Arc (universal frame)
- Problem: hook with concrete, relatable pain or question — no preamble, open with wound
- Journey: explore space — what approaches exist, what fails, what tried; show struggle honestly
- Insight: the "aha" — what learned, discovered, built; name it clearly and early
- Action: what reader/audience does next — specific, low-friction, time-bound where possible
Format-Specific Arc Mapping
- Blog post: arc beats = H2 sections; each H2 opens with sentence naming that beat's purpose
- Marp slide deck: arc beats = section-divider slides (
<!-- class: lead -->title cards); content slides within each section serve that section's narrative beat - Social thread: compressed arc — Problem in tweet 1 (hook), Journey + Insight in tweets 2–5, Action in final tweet
- Talk abstract (CFP-style, 150–300 words): arc in paragraph form, one paragraph per beat
- Lightning talk outline (5–10 min): tighter arc, two or three content beats per section max
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.
- 2d ago First seen · 146 lines · 81 tokens per session scan A 00df84474959
creator is an agent published in the GitHub repository Borda/AI-Rig (25 stars, last pushed 8d ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,283 once invoked, about $0.0004 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 agents, from other repositories
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
blind-author
Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests…