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-chronicle-reducergit 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-chronicle-reducer)<a href="https://agentmods.dev/skills/cratis/ai/cratis-chronicle-reducer"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-chronicle-reducer/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-chronicle-reducer"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-chronicle-reducer.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 | $0.00047 | $0.03680 |
| Opus 5.5 | $0.00019 | $0.01472 |
| Sonnet 5.5 | $0.00009 | $0.00736 |
| Haiku 4.5 | $0.00005 | $0.00368 |
Grade A, and why
cratis-chronicle-reducer 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 today.
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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chronicle reducers
A reducer builds a read model as "current state plus event produces next state",
with real C# control flow. Start with model-bound attributes, use fluent
IProjectionFor<T> when mappings need structure, and choose a reducer when
branching on prior state, calculations or guards read better as code. A reducer
is a normal choice, not a last resort. For the application-code ladder and PDL's
outside-code role, read choosing a style.
Requires Chronicle 19.58.0 for self-reducing read models.
For new .NET reducers, default to self-reducing read models: public static
Reduce methods beside the state, discovered by shape without a marker. Use a
separate IReducerFor<T> for fold-time DI, replay-time instance state or useful
separation; nominate a plain class only when its assembly cannot reference
Chronicle. Self reduction is .NET-only; other SDKs retain
their own contracts. This guidance does not claim Stage renders the self form.
Verified product sources
Sources:
Read references/product-sources.md when you need the source files behind discovery and ownership.
Reverify product sources before claiming support for another version.
Choose the form
- Direct property mapping, counters and sums usually read best as projections. Fluent definitions add mapping structure, not arbitrary per-event code.
- Prior-state branches and guarded calculations often read best as reducers. Explain the state-transition rule, rather than proving both projection APIs incapable. Reducers fold per event source: no native cross-source joins, custom aggregation keys or variant-group wiring.
- Keep the state and transition together by default. Choose
IReducerFor<T>when constructor dependencies, replay instance behavior or a separate data contract make the extra type useful. Prefer event-recorded rates/times over consulting today's service during replay. Never hide durable state on a reducer service instance. - When the assembly cannot reference Chronicle, nominate a plain instance class
through
ChronicleOptions.ExplicitArtifacts.RegisterReducer<PlainReducer>()before creating stores. Supported instance handlers must infer exactly one model. See discovery and nomination.
What ships with it
6 files 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.
- today Changed · -32 tokens per session a601348aa778
- yesterday Changed · +14 lines 1d4434e052e0
- 9d ago Changed · +4 lines 3870d28c24fe
- 10d ago Changed · +3 lines 95108af46cf7
- 11d ago Changed · -3 lines 57433a3ed22c
- 13d ago Changed · +76 lines cb8b1eaa518f
- 14d ago Changed · +19 lines 9d5f9f9b2650
- 18d ago Changed · -3 tokens per session def8c307e1d8
- 20d ago Changed · +16 lines 1dc095c846a1
- 23d ago First seen · 190 lines · 82 tokens per session scan A 0da85afd8cfa
cratis-chronicle-reducer is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 3,680 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
architecture-paradigm-cqrs-es
Applies CQRS and Event Sourcing for read/write separation and audit trails. Use when designing systems with complex domain logic or full state-change history.
cqrs-event-sourcing
CQRS and Event Sourcing patterns for scalable, auditable systems with separated read/write models. Use when building audit-required systems, implementing temporal queries, or designing high-scale applications with complex domain logic.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.