Is the Sentry Instrumentation skill free?

Yes. The skill itself is free from tortastudios/sentry-instrumentation. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Sentry Instrumentation SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Sentry Instrumentation?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Sentry Instrumentation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Sentry Instrumentation

Governed Sentry metrics and gen_ai tracing, enforced by a real AST CI gate.

by tortastudios · tortastudios/sentry-instrumentation

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2d66f7a

Ran the bundled AST CI gate for real against a throwaway retry-loop instrumentation: it correctly flagged a naive sentry_sdk.metrics.incr() call with a dynamically-concatenated name and a raw-exception tag (M001), and passed clean once rewritten to the skill's governed MetricDef + emit_counter pattern -- it even caught my own first attempt at the 'correct' version for emitting inside the loop (M012) before I fixed the placement.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Sentry Instrumentation does

Teaches an agent to add Sentry counters, gauges, durations, and gen_ai.* tracing spans through a governed registry instead of ad-hoc emit calls with raw exception strings or dynamic tag values. Triggers on 'instrument', 'add a metric', 'track duration/failures', 'add a span', or 'trace an agent', and ships a 13-check AST-based CI gate (scripts drop-in) that verifiably blocks ungoverned metrics before merge.

How to install Sentry Instrumentation

git clone https://github.com/tortastudios/sentry-instrumentation
cd sentry-instrumentation
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/sentry-instrumentation

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Sentry Instrumentation

/sentry-instrumentation Governed Sentry metrics and gen_ai tracing, enforced by a real AST CI gate.

It also activates on plain-language prompts like these:

Instrument this payment retry function with a Sentry metric for outcomes
Add a gen_ai tracing span around this agent call using our metric registry
Run the CI gate to check my new Sentry counters aren't ad-hoc emits

Frequently asked questions

Is the Sentry Instrumentation skill free?: Yes. The skill itself is free from tortastudios/sentry-instrumentation. SkillProof publishes the install command and an independent test verdict at no cost.
Does Sentry Instrumentation work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran the bundled AST CI gate for real against a throwaway retry-loop instrumentation: it correctly flagged a naive sentry_sdk.metrics.incr() call with a dynamically-concatenated name and a raw-exception tag (M001), and passed clean once rewritten to the skill's governed MetricDef + emit_counter pattern -- it even caught my own first attempt at the 'correct' version for emitting inside the loop (M012) before I fixed the placement.
What is the Sentry Instrumentation SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Sentry Instrumentation?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Sentry Instrumentation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.