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 skills/gridaco/nothing/etiologynpx skills add gridaco/nothing --skill etiologygit clone --depth 1 https://github.com/gridaco/nothingWhat 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 | $0.00101 | $0.01122 |
| Opus 5 | $0.00051 | $0.00561 |
| Sonnet 5 | $0.00020 | $0.00224 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
etiology 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.
This is a copy
100% identical to etiology — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
etiology
The temptation in a bug fix is to suppress the symptom. The discipline is to know which fix you wrote: the one that addressed the cause, or the one that masked it. Every bug has an etiology — the chain of cause that produced the observable fault — and a fix is only honest once that chain has been traced.
Errors only grow. A bandaid leaks into adjacent call sites, and the next reader inherits both the original defect and the workaround that obscures it. Be fixated on the etiology; the symptom is what alerted you to the bug, not the bug itself. A bandaid is occasionally correct, but it is never the default.
The diagnostic ladder
Before writing the fix, walk the ladder. Each rung is a question the next rung depends on; skipping a rung produces a fix that doesn't know what it is.
- Presentation. What is the user-observable fault? State the symptom precisely — not the suspected cause, the symptom.
- Proximate cause. Which specific code is wrong, and is the defect at the line you would patch, or upstream of it? The line that fires the error is rarely the line that contains it.
- API contract. Was the abstraction we relied on misleading — i.e., would another developer following normal patterns re-trigger the same bug at a different call site? If yes, the defect is in the interface, not the caller.
- Isolated or systemic. Is this a self-contained oversight, or one presentation of a broader pathology in the surrounding code? If broader, scope the fix to the broader cause; patching one of N produces N − 1 future bug reports.
Stating in the PR description which rung you stopped at — and why — keeps the review honest.
Coverage cuts both ways
- Should-have-been covered. The defect slipped a test that ought to exist. The fix carries that test — coverage earned by a regression is the cheapest coverage you will ever buy.
- Impossible to cover. Interactive timing, render-order asymmetries, benchmark-only drift, layered composition where the execution order is the behavior — defects of this kind have no defense once shipped. That raises the bar on the fix, not lowers it. Prefer the underlying refactor; if you must ship a surgical patch, document the constraint at the call site so the next reader sees both the symptom and the rule that keeps it from recurring.
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 · 113 lines · 101 tokens per session scan A 687cbe01fa3f
etiology is a skill published in the GitHub repository gridaco/nothing (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,122 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to etiology, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
docs-svg-kit
Author SVG figures for Grida docs — diff-able, version-controlled vector diagrams embedded in doc pages instead of screenshots. Provides reusable primitives (selection chrome, size badges, anchor pins, resize cursors, click ripples), color/typography tokens, a starter template, and finished examples to crib from.…
editor-perf
Guides performance investigation, benchmarking, and optimization of the Grida Canvas web editor (TypeScript reducer, Immer, React hooks). Use when profiling reducer dispatch cost, diagnosing slow interactions (drag, resize, color change), writing or running editor benchmarks, instrumenting with PerfObserver, or…
sdk-seam
Discipline for the seam between two SDKs (or two sides of one contract) that the same hand writes. The failure mode: "we own both sides" produces dirty contracts no foreign reviewer would accept. The exercise: pretend the other side is FFI, IPC, or a network protocol you cannot rewrite. Spawn an adversarial subagent…
agent-system
Grida AI agent system work: @grida/daemon (DaemonServer, loopback HTTP perimeter, files/workspaces, secrets store, daemon discovery) and @grida/agent (the agent tenant: sessions, providers/BYOK, runtime/tool execution, skills discovery, prompts, tiers, sandbox hosts). Use for packages/grida-daemon/…
ai-models
Research, compare, and update AI model configurations. Covers text model tiers, image and video generation models, image tool models, pricing data sourcing, and provider-cost metering against prepaid org credit. Use when bumping model versions, adding new models, updating pricing, or auditing model specs against…
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…