Borrowing it
Nothing to install: this file belongs to Cratis/VerticalSlices. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cratis/VerticalSlices/main/.ai/skills/add-traces/SKILL.mdgit clone --depth 1 https://github.com/Cratis/VerticalSlicesWrote 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/verticalslices/add-traces)<a href="https://agentmods.dev/skills/cratis/verticalslices/add-traces"><img src="https://agentmods.dev/badge/skills/cratis/verticalslices/add-traces/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/verticalslices/add-traces"><img src="https://agentmods.dev/badge/skills/cratis/verticalslices/add-traces.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 | $0.00073 | $0.01902 |
| Opus 5.5 | $0.00029 | $0.00761 |
| Sonnet 5.5 | $0.00015 | $0.00380 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade A, and why
add-traces 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 1mo 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 add-traces — 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Traces to a Class
Chronicle uses the Fundamentals Traces pattern from Cratis.Traces. Never call System.Diagnostics.ActivitySource directly. Always use the source-generator [Span] attribute and IActivitySource<T>.
Overview
- Create a
*Traces.cscompanion file with[Span]methods. - Register
IActivitySource<T>viaservices.AddNamedActivitySource(WellKnown.MeterName)inChronicleMetersExtensions(one call covers all types via open-generic keyed DI). - Inject
[FromKeyedServices(WellKnown.MeterName)] IActivitySource<TTarget>into the class. - Call the generated extension methods and apply tags via
TagExtensions. - Update specs to pass
new ActivitySource<T>()(not a substitute).
DI registration architecture
Chronicle's ActivitySource follows the same keyed DI pattern as Meter:
| Layer | Meter | ActivitySource |
|---|---|---|
Shared well-known instance (keyed by WellKnown.MeterName) |
Meter("Cratis.Chronicle") |
System.Diagnostics.ActivitySource("Cratis.Chronicle") |
Per-type wrapper (keyed by WellKnown.MeterName) |
IMeter<T> / Meter<T> |
IActivitySource<T> / ActivitySource<T> |
| Registered by | services.AddNamedMeter(WellKnown.MeterName) |
services.AddNamedActivitySource(WellKnown.MeterName) |
Both calls are made from ChronicleMetersExtensions.AddChronicleMeters(). They use open-generic keyed DI (TryAddKeyedSingleton(typeof(IMeter<>), name, typeof(Meter<>))), so any new type added to a keyed-injected class is automatically covered — no per-type registration step is needed.
Step 1 — Create a *Traces.cs companion file
Each class that needs tracing gets its own *Traces.cs file in the same folder.
// Copyright (c) Cratis. All rights reserved.
// Licensed under the MIT license. See LICENSE file in the project root for full license information.
using System.Diagnostics;
using Cratis.Traces;
namespace Cratis.Chronicle.<Namespace>;
#pragma warning disable SA1600 // Elements should be documented
#pragma warning disable MA0048 // File name must match type name
#pragma warning disable SA1402 // File may only contain a single type
internal static partial class <ClassName>Traces
{
[Span("cratis.chronicle.<domain>.<operation>", ActivityKind.Internal)]
internal static partial IActivityScope<<ClassName>> <OperationName>(this IActivitySource<<ClassName>> source);
}
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.
- 1mo ago First seen · 200 lines · 73 tokens per session scan A 8aaebfa7a713
add-traces is a skill published in the GitHub repository Cratis/VerticalSlices (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,902 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to add-traces, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cratis-chronicle-cli-operations
Inspect and operate a running Chronicle server with the cratis CLI - contexts and connection resolution, machine-readable output, failed partitions, observers, event sequences, read models, projections and jobs, and the authorization discipline for replay, retry, quarantine clearing and other mutations. Use when the…
cratis-lens-browser-extension
Use the Cratis Lens browser extension against a running Cratis Arc application — building and side-loading it, what the Arc app must already serve for Lens to work, switching the active user and tenant, and executing a command or query from the popup. Use when setting Lens up, when Lens does not detect an Arc app, or…
cratis-arc-observable-query-http
Inspect a Cratis Arc observable query from a terminal with curl or another plain HTTP client — snapshot GET, waiting for the first result, Server-Sent Events streaming, and long polling, plus the exact query-string keys, status codes, and payload shape. Use when debugging or exploring an observable query without…
cratis-cli-terminal-workbench
Navigate the cratis CLI's terminal Workbench - the full-screen TUI launched with cratis chronicle workbench. Use when exploring a running Chronicle store interactively rather than answering one question with a single command, when locating an observer, failure, event type, projection or read model by name, or when…
cratis-engineering-regression-cluster
Stop fixing instances when one surface keeps breaking - name the failure class, add the gate that owns it, prove the gate fails, then fix the instance. Use when a third bug, regression, revert or review finding lands on the same screen, endpoint, command, workflow or module, when the same kind of fix keeps being…
cratis-screenplay-toolchain
How to run and check Cratis Screenplay .play models: locating the model, choosing the standalone screenplay tool or the cratis CLI, the exact command behind each verdict V1 to V5 and what a pass looks like, the executable and renderable subsets, reading PLAY, STAGE and CLI-RENDER diagnostics, traps, and a compiled…