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/inspect-running-chroniclenpx skills add Cratis/AI --skill inspect-running-chroniclegit 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/inspect-running-chronicle)<a href="https://agentmods.dev/skills/cratis/ai/inspect-running-chronicle"><img src="https://agentmods.dev/badge/skills/cratis/ai/inspect-running-chronicle.svg" alt="Measured on agentmods" 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 | $0.00106 | $0.01202 |
| Opus 5 | $0.00053 | $0.00601 |
| Sonnet 5 | $0.00021 | $0.00240 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
inspect-running-chronicle scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **observable-query-curl** — for exercising an application's own observable query endpoints over HTTP, which is a different surface from the store's management API. Copies of this mod
1 near-identical copy found in the catalogue:
- inspect-running-chronicle — 100% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect a Running Chronicle
Source code says what should happen. When the question is what is happening in a live store — a projection that will not move, an observer that stopped, an event you are not sure was appended — read the server instead of the code. The cratis CLI is how.
Do not guess command names from this file. The CLI ships its own complete, versioned catalog and that is the authority:
cratis llm-context # every command, option and argument as JSON
cratis <group> --help # the same, one group at a time
This skill covers when to reach for the CLI and how to read what comes back. The catalog covers what to type.
Setting it up in a project
Once per project, so every agent working it can reach the store:
cratis init # detects the AI tools in use and writes CHRONICLE.md + a chronicle-cli skill
cratis init --refresh # re-capture after upgrading the CLI
Two things worth knowing before running it:
- The embedded catalog is a snapshot, not a live lookup. After a CLI upgrade it still describes the older surface;
cratis initreports the mismatch and--refreshfixes it. - If the repository's instruction file (
AGENTS.md,CLAUDE.md,.github/copilot-instructions.md) is supplied by a shared package or generated adapter, pass--no-context. Keep project-specific Chronicle connection guidance in the repository-owned.cratis/PROJECT.mdorCHRONICLE.md; never patch packaged/generated bytes or depend on legacy corpus synchronization.
Reaching the right server
Resolution order is --server → CHRONICLE_CONNECTION_STRING → the active context → chronicle://localhost:35000. Prefer a named context over repeating a connection string:
cratis context create dev --server chronicle://localhost:35000
cratis context set dev
Be deliberate about which store you are pointed at. The same commands read production and a local container, and several of them are destructive. Confirm the context before running anything that writes.
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 Changed · +8 lines 28f377264172
- 6d ago First seen · 72 lines · 106 tokens per session scan A d896c80b4a95
inspect-running-chronicle is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,202 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
inspect-running-chronicle
Inspect or operate a running Chronicle server with the cratis CLI - list failed partitions, read why an observer is stuck, replay a partition, browse events, event types, read models, projections and jobs. Use when a question is about the state of a live store rather than the source code, when a projection will not…
observable-query-curl
Practical guidance for debugging and exploring Cratis Arc observable queries with cURL or other plain HTTP clients. Use this whenever the user mentions observable queries together with cURL, curl, HTTP GET debugging, waiting for the first payload, Server-Sent Events, SSE, streaming JSON, or long polling. Also use it…
diagnose-slice
Use this skill to diagnose why a Cratis slice misbehaves — read model not updating, TypeScript proxy missing, command rejected unexpectedly, projection/observer quarantined, AutoMap mismatch, reactor side effects not appended, or specs flaking. Symptom → likely cause → the rule/skill that owns the fix. Use when…
review-performance
Use this skill when asked to check for performance issues, inefficiencies, or scalability problems in a Cratis-based project. Covers Chronicle projections, MongoDB query patterns, .NET allocations, and React render overhead.
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.