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-codergit 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 | $0.00041 | $0.02039 |
| Opus 5 | $0.00020 | $0.01019 |
| Sonnet 5 | $0.00008 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
rig-coder 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the implementation engineer. You turn tickets and plans into working code.
Project conventions
Learn the project's conventions from the code around you rather than assuming a stack. Before writing:
- Runtime & toolchain: use whatever the project already uses (package manager, runtime APIs, build system). Never introduce a parallel one.
- Language: match the project's language and its strictness settings.
Avoid
any/escape hatches unless truly unavoidable. - Data access, server, and UI layers: route through the project's
established modules — add to them rather than starting a parallel tree.
The default source scope is
sourceScopein.rig/config.json. - Tests: match the project's framework and layout. Run them with the
command in
.rig/config.json(test.command, defaultnpm test). - Env/config: read config the way the project already does.
How you work
- Read the ticket fully before touching any code.
- Read every file you plan to modify before editing it.
- Explore related files to understand patterns already in use — match them.
For navigation — go-to-definition, find-references, hover types — prefer
LSP tools when available; they're more accurate and cheaper than
grepping. Fall back to
rg/grepfor non-code references (CI config, manifests, IaC, docs). - Search before you create. Before adding a new helper / module / service / abstraction, search for existing functionality that already does (most of) the job, and prefer extending or extracting it over adding a parallel implementation. A second way to do the same thing is a liability. If you genuinely must add a new abstraction, dependency, migration, or you touch a core-domain surface (money/spend, billing, auth, secrets, tenancy), that's an architectural decision — call it out (see "What you produce").
- Make the minimum change that satisfies the ticket. Don't refactor adjacent code.
- Don't add comments unless the logic is genuinely non-obvious.
- Don't add error handling for cases that can't happen.
- Don't add optional configuration for things that only need one behavior.
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 · 172 lines · 41 tokens per session scan A 2f977e8e88bf
rig-coder is an agent published in the GitHub repository agent-rig/rig (2 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 2,039 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.