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/cratis/ai/discover-implementationsnpx skills add Cratis/AI --skill discover-implementationsgit clone --depth 1 https://github.com/Cratis/AIWhat 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 | $0.00069 | $0.01026 |
| Opus 5 | $0.00034 | $0.00513 |
| Sonnet 5 | $0.00014 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
discover-implementations 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- discover-implementations — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wire convention-based discovery for a set of implementations behind an abstraction.
The pattern in one line
Inject IInstancesOf<TInterface> from Cratis.Types. Mark implementations with [Singleton]. Delete any services.AddSingleton<TInterface, Impl>() lines that registered them.
When this skill applies
The consumer of an abstraction needs to iterate, filter, or fan out to every registered implementation. Common shapes:
*Handlers,*Filters,*Validators,*Formatters,*Strategies,*Providers,*Resolvers— anything plural that delegates to a set.- A dispatcher that picks the right implementation by calling
CanHandle(...)and forwarding to the matching one. - A composite that fans a single input out to all implementations and aggregates results.
When it does NOT apply
- The consumer needs one implementation chosen at composition time → constructor-inject the concrete interface and let normal DI resolve
IFoo → Foo. - The method returns a sequence of values to a caller →
IEnumerable<T>(orIReadOnlyList<T>, etc.) is still the right return type. The rule is only about injecting implementations of an abstraction.
Step 1 — Confirm the implementations are discoverable
IInstancesOf<T> discovers types by convention from loaded assemblies. The only requirements:
- Each implementation is a non-abstract
public class. - It implements the interface directly (not via another layer that hides it).
No assembly attribute is needed — the Cratis framework's type discovery picks them up automatically.
Step 2 — Mark implementations as singletons (default)
[Singleton]
public class EventResultHandler(IEventTypes eventTypes) : IReactorSideEffectHandler
{
public bool CanHandle(ReactorContext context, object value) => /* ... */;
public Task Handle(ReactorContext context, object value) => /* ... */;
}
Add using Cratis; if [Singleton] is unresolved.
Skip [Singleton] only when the implementation must be transient — i.e. it holds per-call state that cannot be shared. The convention IFoo → Foo still applies for transients; do not register them explicitly.
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 · 96 lines · 69 tokens per session scan A 907a0f4f3d06
discover-implementations is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,026 once invoked, about $0.0003 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 skills, from other repositories
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.
add-concept
Use this skill when asked to create a strongly-typed domain identifier or value (such as ProjectId, AuthorName, InvoiceNumber) in a Cratis-based project. Produces a ConceptAs record with the correct conversions and sentinel values.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
cratis-command
Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…
add-traces
Use this skill when asked to add OpenTelemetry tracing to a class in a Cratis Chronicle Kernel project. Produces Traces.cs companion files using the [Span] source-generator pattern from Cratis.Traces, registers IActivitySource as a keyed DI service, and injects it into the target class.