Conversation
Overall package sizeSelf size: 4.78 MB Dependency sizes| name | version | self size | total size | |------|---------|-----------|------------| | import-in-the-middle | 2.0.6 | 81.92 kB | 816.75 kB | | dc-polyfill | 0.1.10 | 26.73 kB | 26.73 kB |🤖 This report was automatically generated by heaviest-objects-in-the-universe |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #7568 +/- ##
==========================================
- Coverage 80.32% 80.31% -0.01%
==========================================
Files 733 733
Lines 31546 31546
==========================================
- Hits 25338 25336 -2
- Misses 6208 6210 +2 Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This comment has been minimized.
This comment has been minimized.
BenchmarksBenchmark execution time: 2026-02-23 08:59:47 Comparing candidate commit 4311b6c in PR branch Found 0 performance improvements and 0 performance regressions! Performance is the same for 231 metrics, 29 unstable metrics. |
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tlhunter
left a comment
tlhunter
left a comment
There was a problem hiding this comment.
Seems fine... But does every LLM call now use a ton of tokens?
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 92e3cb67f6
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
The token counts are as follows, keep in mind, at startup, only the front matter (skill name + description are loaded, few hundred tokens). When the llm triggers the skill to use it, only |
- Add missing imports (assert, ANY_STRING) to test template - Fix error.stackTrace → error.stack to match dd-trace constants - Remove incorrect claim that orchestrion auto-handles CJS/ESM splits - Convert all cross-references to proper markdown links Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
| This skill should be used when the user asks to "add a new integration", | ||
| "create a new plugin", "instrument a library", "add instrumentation for", | ||
| "write a plugin", "create instrumentation", "new dd-trace plugin", | ||
| "add tracing for", "TracingPlugin", "DatabasePlugin", "CachePlugin", | ||
| "ClientPlugin", "ServerPlugin", "CompositePlugin", "ConsumerPlugin", | ||
| "ProducerPlugin", "addHook", "shimmer.wrap", "orchestrion", | ||
| "bindStart", "bindFinish", "startSpan", "diagnostic channel", | ||
| "runStores", "reference plugin", "example plugin", "similar integration", | ||
| or needs to build, modify, or debug the instrumentation and plugin layers | ||
| for a third-party library in dd-trace-js. |
There was a problem hiding this comment.
Nit: I think there's a difference between adding new instrumentation, and adding a new plugin. You can add a new plugin without having it be related to instrumentation. In that case, do we really want to the agent to try this skill?
There was a problem hiding this comment.
Taken into account, though for placing the new plugin creation into another skill, I do not think that's the right move. Considering that plugins rely on the instrumentation side, and the LLM should have some context on instrumentations when writing any plugin.
* add APM integration skill, which covers instrumentation, plugins, a new integration guide, and reference integrations.
* add APM integration skill, which covers instrumentation, plugins, a new integration guide, and reference integrations.
3 participants
Adds a Claude skill for integrations. Uses skill best practices including limiting Skill.MD to under 300 lines, and using reference links in the MD to reference files that hold more specific information. Pulls in information from the recently added PR for adding a new integration, and adds this information as a reference for new integration implementation guide. Prioritizes orchestrion for writing new integrations.
#7564
What does this PR do?
Motivation
Additional Notes