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 agent-rig/rig --skill rig-spikegit clone --depth 1 https://github.com/agent-rig/rigWrote 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/agent-rig/rig/rig-spike)<a href="https://agentmods.dev/skills/agent-rig/rig/rig-spike"><img src="https://agentmods.dev/badge/skills/agent-rig/rig/rig-spike/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/agent-rig/rig/rig-spike"><img src="https://agentmods.dev/badge/skills/agent-rig/rig/rig-spike.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 | $0.00114 | $0.02263 |
| Opus 5.5 | $0.00046 | $0.00905 |
| Sonnet 5.5 | $0.00023 | $0.00453 |
| Haiku 4.5 | $0.00011 | $0.00226 |
Grade A, and why
rig-spike 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 1mo 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Spike
A spike is a time-boxed investigation whose deliverable is knowledge, not shipped code. You answer a specific question, surface the trade-offs, and recommend a path — so the team can plan implementation with confidence instead of guessing.
Use a spike when the work is uncertain: feasibility is unknown, there are multiple viable approaches, an unfamiliar API/library is in play, or scope can't be estimated until something is prototyped. If the path is already clear and it's just work to be done, skip the spike and go straight to implementation planning.
Configuration
Reads .rig/config.json:
sourceScope[0]— the default code scope explorers map first (default:src).tracker.provider—linear|github|none(default:none). Whennone, skip all tracking-ticket steps and deliver the writeup in chat only. When set, optionally create aSpike:tracking ticket and post findings back to it.tracker.team/tracker.project— where a Linear tracking ticket is filed, when the provider islinear.agents.architect— the project's name for the canonicalarchitectrole (default:architect).ExploreandPlanare Claude Code built-ins and are used as-is.style.guideFile— the writing style for the findings writeup (default:.claude/STYLE.md).
If the file is absent, use the defaults above (treat the tracker as
none) and note you're running unconfigured.
Core rules of a spike
- Time-box it. Decide the budget up front (default: half a day / ~4h of effort). The goal is enough signal to decide, not a complete build.
- The output is a writeup, not a PR. Any code is throwaway prototype used to learn — it does not get merged. Mark prototype branches clearly and don't open a PR-to-trunk from them.
- End with a recommendation and concrete next steps (usually: tickets to create, or a "don't do this" with the reason).
- Be honest about what you couldn't verify. Lead with the verdict, back
it with evidence, and mark anything you can't support with
file:line(or a run/probe result) asunverifiable— never pad a recommendation with confidence you didn't earn. - Pin the codebase state. Record the commit SHA you investigated against
(
git rev-parse HEAD) plus the date, so the recommendation is reproducible and its staleness is obvious once the trunk moves on.
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.
- 1mo ago First seen · 180 lines · 114 tokens per session scan A 1dac3c664968
rig-spike is a skill published in the GitHub repository agent-rig/rig (3 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 2,263 once invoked, about $0.0005 per session on Opus 5.5. 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
proxmox-full
Complete Proxmox VE hypervisor management via REST API - VMs, containers, snapshots, backups, storage.
a-philosophy-of-software-design
Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.
aerodynamicist
Think and work like an expert Aerodynamicist. Use when a task calls for Aerodynamicist judgment. 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…
agronomist
Think and work like an expert Agronomist. Use when a task calls for Agronomist judgment. Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed models, partial budgets, and AgroEcoList reporting while treating…
algebraist
Think and work like an expert Algebraist. Use when a task calls for Algebraist judgment. Reasons from carriers, operations, and morphisms through isomorphism theorems, universal properties, exact-sequence and homological tools (Ext, Tor, snake lemma), and computational systems like GAP, Magma, SageMath, and Lean while…
astrodynamicist
Think and work like an expert Astrodynamicist. Use when a task calls for Astrodynamicist judgment. Reasons from two-body plus perturbation force models through Cowell/Encke propagation, batch LS and EKF orbit determination, SPICE/Horizons ephemerides, CCSDS OEM/CDM exchanges, and TEME–GCRF frame discipline while…