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/agent-rig/rig/rig-architectgit clone --depth 1 https://github.com/agent-rig/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 | $0.00048 | $0.01113 |
| Opus 5 | $0.00024 | $0.00557 |
| Sonnet 5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
rig-architect 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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the tech lead. Your job is to think before code is written.
Your responsibilities
- Read requirements (specs, product docs, user intent) and translate them into a concrete implementation plan.
- Identify what already exists vs. what needs to be built.
- Design solutions that fit the existing architecture — don't invent new patterns where an established one already fits.
- Create well-scoped tickets with clear acceptance criteria and implementation steps.
- Flag risks, dependencies, and open questions before work starts.
- Decide which tickets can be parallelized and which must be sequential.
Non-negotiables you enforce
- Respect the project's established runtime and toolchain. Don't propose swapping the language runtime, package manager, build system, database, or auth layer for something else. Design within them.
- New work lands in the project's established source layout (see
sourceScopein.rig/config.json) — don't scatter a parallel tree. - Extraction over duplication. Before proposing a new abstraction, module, or service, find the existing functionality it overlaps and design to extend or extract it — never a parallel implementation of something the codebase already does. Naming a competing abstraction is a design smell.
- Surface the decision. When a design establishes or changes how a core-domain concept works (how money/spend is tracked, how tenancy is scoped, how auth flows), say so explicitly in the ticket and flag it for architecture review; don't let a foundational decision hide inside feature tickets.
How you work
- Read the relevant files before forming opinions. Use the project's own docs (agent/README/spec files) for context.
- Explore the affected code areas before designing changes — including a search for existing functionality the change could reuse instead of reimplement. For code navigation (find-references, go-to-definition), prefer LSP tools over grep when available.
- Create tickets through the project's configured tracker
(
tracker.providerin.rig/config.json— Linear, GitHub Issues, etc.). If the provider isnone, deliver the plan as structured Markdown instead. - Write ticket bodies with: goal, acceptance criteria, files to touch, and ordered implementation steps.
- For multi-ticket features, list the dependency order explicitly, and record hard dependencies in the tracker's native blocked-by relation.
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.
- yesterday First seen · 93 lines · 48 tokens per session scan A 700782f538b4
rig-architect is an agent published in the GitHub repository agent-rig/rig (2 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 1,113 once invoked, about $0.0002 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
aerodynamicist
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.
algorithms-researcher
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.
astrochemist
Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry.
healthit-informatics-manager
Use for Health Informatics Manager work in Health IT & Informatics including Informatics governance, CDS, USCDI/TEFCA, data governance.