OpenInference is a set of conventions and instrumentation plugins for tracing AI applications with OpenTelemetry. It helps developers record language-model calls, retrieval from vector stores, and external tool use for analysis in compatible observability backends. The catalogue entries support instrumentation and use of these tracing conventions.
Borrowing it
Nothing to install: this file belongs to Arize-ai/openinference. 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/Arize-ai/openinference/main/.claude/skills/python-canary-fix/SKILL.mdgit clone --depth 1 https://github.com/Arize-ai/openinferenceWrote 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/arize-ai/openinference/python-canary-fix)<a href="https://agentmods.dev/skills/arize-ai/openinference/python-canary-fix"><img src="https://agentmods.dev/badge/skills/arize-ai/openinference/python-canary-fix/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/arize-ai/openinference/python-canary-fix"><img src="https://agentmods.dev/badge/skills/arize-ai/openinference/python-canary-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 56 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 57 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00053 | $0.02447 |
| Opus 5.5 | $0.00021 | $0.00979 |
| Sonnet 5.5 | $0.00011 | $0.00489 |
| Haiku 4.5 | $0.00005 | $0.00245 |
Grade A, and why
python-canary-fix 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Canary Fix
Investigate failures in the Python canary cron (python-cron.yaml) workflow and propose a fix for Python instrumentation packages.
When to Use
- User mentions Python canary cron failures
- A scheduled trigger reports canary failures
- User asks to investigate
*-latesttest environment failures - Invoked automatically by the
auto-fixjob inpython-cron.yaml
Workflow
Each failing package is investigated and fixed independently, with its own branch and its own PR. Do not bundle fixes for multiple packages together, even when they share an apparent root cause — keep PRs scoped to a single instrumentor so they can be reviewed, reverted, and released independently.
When invoked by the scheduled auto-fix job, the workflow already runs one job per failing package and creates the branch before Claude starts. In that mode, follow the prompt's package scope, do not commit, push, or open a PR, and instead write:
.scratch/pr-title.txt: a one-line conventional-commit PR title..scratch/pr-body.md: a concise PR body with root cause, fix, and commands run.
The workflow will commit, push, and open the PR after Claude exits. It does not re-validate your fix in-workflow — the opened PR's own CI runs this package's -latest envs and is the gate (branch protection blocks merging until CI is green), so still aim to make the failing env pass, but an imperfect fix becomes a red PR for a human to finish rather than being discarded. The workflow also skips invoking you entirely when an open auto-fix PR for the package already exists, so you do not need to guard against that case. For manual use outside CI, continue to open one PR per package yourself.
In CI auto-fix mode, the workflow downloads the failed tox logs before Claude starts. Always read .scratch/failure-logs/*.log first and use the first traceback or assertion from those local logs as the primary signal. Do not call gh run view --log or gh run view --log-failed for the same in-progress run unless the local logs are missing or clearly incomplete.
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 · 78 lines · 53 tokens per session scan A c26d0a84b16d
python-canary-fix is a skill published in the GitHub repository Arize-ai/openinference (1,291 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 2,447 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 2026-08-30.
Other skills, from other repositories
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
observability-phoenix
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
observability
Use when instrumenting a service from the inside so an incident can be explained from telemetry alone — wiring OpenTelemetry logs, metrics and traces, standing up a Collector, exporting via OTLP, and defining telemetry-driven alerts. NOT outside-in uptime probes, on-call rotation, or who-gets-paged (that is…
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
debugging-with-wide-events
Use when investigating production behavior by querying wide events (a slow route, an error spike, a suspicious deploy, "why is this happening for account X"). Covers the data model, the symptom-to-query workflow, and standing queries worth running.
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.