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 Cratis/AI --skill cratis-performance-reviewgit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-performance-review)<a href="https://agentmods.dev/skills/cratis/ai/cratis-performance-review"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-performance-review/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/cratis/ai/cratis-performance-review"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-performance-review.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 | $0.00076 | $0.01505 |
| Opus 5 | $0.00038 | $0.00753 |
| Sonnet 5 | $0.00015 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
cratis-performance-review 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cratis performance review
Most performance findings in a Cratis application are shape problems, not hot-loop problems: a projection that has to re-read, a query that materializes before it filters, a payload nobody uses. They are cheap to fix while the change is open and expensive once data has grown behind them.
Two things make this stack different. A projection must be able to replay the entire history — a cost that is invisible at development volumes and fatal at production ones. And an event is permanent, so an oversized event is a storage and replay cost that never goes away.
Verified product sources
| Package | Version | Purpose |
|---|---|---|
Cratis.Chronicle |
16.45.2 |
Observers, projections, reducers, reactors, replay |
Cratis.Arc.Core |
22.10.4 |
Query return shapes and server-side paging |
@cratis/components |
current | DataTable paging surface |
Reverify against the owning product repository before asserting a framework behavior this file does not already state.
Route near misses
- General correctness and maintainability: use
cratis-code-review. Its performance section is the pass-by list; this skill is the focused one. When both have run, do not restate the same finding twice. - Adding paging to a query rather than judging one: use
cratis-arc-query-paging. That skill is authoritative on the mechanism; this one does not override it. - Security or data exposure: use
cratis-security-review. An over-fetching payload is a finding for both — say which lens produced it.
Step 1 — Chronicle and event sourcing
- A projection joins on events, never on a read model. A read-model join forces a re-read the projection engine cannot optimize, and it makes the projection depend on another observer's position.
- A reactor does not re-query the event log inside its handler. The event it
received already carries what it needs. (Reactor dispatch is by the handler's
first parameter type — the method name is free, so look for the event-typed
parameter, not for a method called
On.) - A new projection can replay all historical events without failing. Ask it explicitly: at production volume, does this projection complete a full replay?
- Events are small. No large blob and no base64 payload embedded in an event; put the content elsewhere and carry a reference.
- No eager load of a whole event sequence without paging or filtering.
- AutoMap is on by default. Hand-mapping every property is both a maintenance and a cost problem — and, since AutoMap runs anyway, it does not save the work it appears to.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 140 lines · 76 tokens per session scan A 92c089ca848d
cratis-performance-review is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,505 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 2026-09-08.
Other skills, from other repositories
code-analysis
Use the free built-in .NET SDK analyzers and analysis levels with gradual Roslyn warning promotion. USE FOR: the repo wants first-party .NET analyzers; CI should fail on analyzer warnings; the team needs AnalysisLevel or AnalysisMode guidance. DO NOT USE FOR: third-party analyzer selection by itself; formatting-only…
sonarjs
Use SonarJS-derived rules in .NET repositories that ship JavaScript or TypeScript frontends and need deeper bug-risk, code-smell, or cognitive-complexity checks than a minimal ESLint baseline. USE FOR: SonarQube, SonarCloud, or eslint-plugin-sonarjs setups; frontend code smells; cognitive complexity and deeper…
meziantou-analyzer
Use the open-source free Meziantou.Analyzer package for design, usage, security, performance, and style rules in .NET. Use when a repo wants broader analyzer coverage with a single NuGet package. USE FOR: the repo uses or wants Meziantou.Analyzer; the team wants one analyzer pack that covers design, usage, security…
dotnet-techne-csharp-api-design
Use when designing or changing public C#/.NET APIs with compatibility and versioning constraints. Keywords: breaking change, API design, backward compatibility, binary compatibility, deprecation strategy, versioning.
dotnet-techne-csharp-type-design-performance
Use when designing types and collections for hot paths and low-allocation .NET code. Keywords: readonly struct, sealed class, ValueTask, Span, FrozenDictionary, FrozenSet, allocation optimisation.
dotnet-techne-inspect
Use when you need to inspect NuGet package APIs, list public types, or decompile method/property signatures. Keywords: inspect package API, list types, decompile type, method signatures, NuGet interface.