Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .claude/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .agents/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .cursor/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .gemini/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .github/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "sentry-elixir-sdk" agent skill from https://github.com/getsentry/sentry-for-ai/tree/main/skills-legacy/sentry-elixir-sdk into .opencode/skills/sentry-elixir-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sentry-elixir-sdk", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
sentry-elixir-sdk
GitHub stars
268
Token cost
~3.5k tokens
SKILL.md length
1,145 words
Files
5 (incl. references)
Skills in repo
32
Repo updated
First seen
Licence
Apache-2.0
At a glance
Full Sentry SDK setup for Elixir. An agent skill from getsentry/sentry-for-ai.
Works in 4 steps: Detect → Recommend → Guide → …
Asked to add Sentry to Elixir
SKILL.md covers Invoke This Skill When, Phase 1: Detect, Phase 2: Recommend and Phase 3: Guide, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sentry Elixir SDK is an agent skill from getsentry/sentry-for-ai, published by the product's own GitHub organization. Full Sentry SDK setup for Elixir. Use when asked to "add Sentry to Elixir", "install sentry for Elixir", or configure error monitoring, tracing, logging, or crons for Elixir, Phoenix, or Plug applications. Supports Phoenix, Plug, LiveView, Oban, and Quantum.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/crons.md`, `references/error-monitoring.md` and `references/logging.md`).
It sits in AI & LLM Engineering, covering LLM observability, Scheduled and recurring tasks and Observability. It works with Sentry, Elixir and OpenTelemetry. The repository describes itself as: Teach your AI coding assistant how to use Sentry - setup, debugging, alerts, and more. The licence is Apache-2.0.
When your agent uses it
Asked to add Sentry to Elixir
Install sentry for Elixir
Configure error monitoring
Crons for Elixir
Example prompts
“add Sentry to Elixir”
“install sentry for Elixir”
“/sentry-elixir-sdk”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d8fd106. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are elixir and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.sentry.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sentry Elixir SDK loads about 3.5k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 1,145 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~69
When it runs· the whole SKILL.md, loaded when a task matches
~3.5k
With references· SKILL.md plus every file in references/, read only if the agent opens them
~12k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/sentry-elixir-sdk/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
sentry-elixir-sdk
description
Full Sentry SDK setup for Elixir. Use when asked to "add Sentry to Elixir", "install sentry for Elixir", or configure error monitoring, tracing, logging, or crons for Elixir, Phoenix, or Plug applications. Supports Phoenix, Plug, LiveView, Oban, and Quantum.
Opinionated wizard that scans your Elixir project and guides you through complete Sentry setup.
Invoke This Skill When
User asks to "add Sentry to Elixir" or "set up Sentry" in an Elixir or Phoenix app
User wants error monitoring, tracing, logging, or crons in Elixir or Phoenix
User mentions sentry hex package, getsentry/sentry-elixir, or Elixir Sentry SDK
User wants to monitor exceptions, Plug errors, LiveView errors, or scheduled jobs
Note: SDK versions and APIs below reflect Sentry docs at time of writing (sentry v13.2.0, requires Elixir ~> 1.13).
Always verify against docs.sentry.io/platforms/elixir/ before implementing.
Phase 1: Detect
Run these commands to understand the project before making any recommendations:
# lib/my_app/application.ex
def start(_type, _args) do
Logger.add_handlers(:my_app) # activates the :sentry_handler configured above
children = [
MyAppWeb.Endpoint
# ... other children
]
Supervisor.start_link(children, strategy: :one_for_one)
end
Phoenix Integration
lib/my_app_web/endpoint.ex
elixir
defmodule MyAppWeb.Endpoint do
use Sentry.PlugCapture # Add ABOVE use Phoenix.Endpoint (Cowboy adapter only)
use Phoenix.Endpoint, otp_app: :my_app
# ...
plug Plug.Parsers,
parsers: [:urlencoded, :multipart, :json],
pass: ["*/*"],
json_decoder: Phoenix.json_library()
plug Sentry.PlugContext # Add BELOW Plug.Parsers
# ...
end
Note:Sentry.PlugCapture is only needed for the Cowboy adapter. Phoenix 1.7+ defaults to Bandit, where PlugCapture is harmless but unnecessary. Sentry.PlugContext is always recommended — it enriches events with HTTP request data.
LiveView errors — lib/my_app_web.ex
elixir
def live_view do
quote do
use Phoenix.LiveView
on_mount Sentry.LiveViewHook # captures errors in mount/handle_event/handle_info
end
end
Plain Plug Application
elixir
defmodule MyApp.Router do
use Plug.Router
use Sentry.PlugCapture # Cowboy only
plug Plug.Parsers, parsers: [:urlencoded, :multipart]
plug Sentry.PlugContext
# ...
end
For Each Agreed Feature
Walk through features one at a time. Load the reference file for each, follow its steps, and verify before moving to the next:
Feature
Reference file
Load when...
Error Monitoring
${SKILL_ROOT}/references/error-monitoring.md
Always (baseline)
Tracing
${SKILL_ROOT}/references/tracing.md
Phoenix / Ecto / OpenTelemetry detected
Logging
${SKILL_ROOT}/references/logging.md
LoggerHandler or Sentry Logs setup
Crons
${SKILL_ROOT}/references/crons.md
Oban, Quantum, or periodic jobs detected
For each feature: Read ${SKILL_ROOT}/references/<feature>.md, follow steps exactly, verify it works.
Configuration Reference
Key Config Options
Option
Type
Default
Purpose
:dsn
string | nil
nil
SDK disabled if nil; env: SENTRY_DSN
:environment_name
atom | string
"production"
e.g., :prod; env: SENTRY_ENVIRONMENT
:release
string | nil
nil
e.g., "my-app@1.0.0"; env: SENTRY_RELEASE
:sample_rate
float
1.0
Error event sample rate (0.0–1.0)
:enable_source_code_context
boolean
false
Include source lines around errors
:root_source_code_paths
[path]
[]
Required when source context is enabled
:in_app_otp_apps
[atom]
[]
OTP apps whose modules are "in-app" in stacktraces
:before_send
(event -> event | nil) | {m, f}
nil
Hook to mutate or drop error events
:after_send_event
(event, result -> any) | {m, f}
nil
Hook called after event is sent
:filter
module
Sentry.DefaultEventFilter
Module implementing Sentry.EventFilter
:max_breadcrumbs
integer
100
Max breadcrumbs per process
:max_stacktrace_arg_length
integer
10000
Max length (in graphemes) of each inspected function argument in stacktrace vars (v13.2.0+)
:dedup_events
boolean
true
Deduplicate identical events within ~30 seconds
:tags
map
%{}
Global tags sent with every event
:traces_sample_rate
float | nil
nil
Non-nil enables tracing (requires OTel setup)
:traces_sampler
fn | {m, f} | nil
nil
Custom per-transaction sampling
:enable_logs
boolean
false
Enable Sentry Logs Protocol (v12.0.0+)
:scrubber
keyword
[]
Scrubber config (v13.1.1+); keys: :conn_private_allow_list (list of atoms kept from Plug.Conn.private)
:test_mode
boolean
false
Capture events in-memory for testing
Show full SKILL.md (411 more words)Show less
Default PII Guidance
Most Sentry SDKs expose a send-default-PII option. As of sentry v12, the Elixir SDK does not expose a send_default_pii config option in its documented option list or current config schema, so do not add a non-existent option. For richer user context, use Sentry.PlugContext and explicitly set allowed fields with Sentry.Context.set_user_context/1, then scrub with :before_send if needed. If a future Elixir SDK release adds send_default_pii, recommend setting it.
Automatic PII Scrubbing: As of v13.1.0, stacktrace frame variables and FunctionClauseError/Phoenix.ActionClauseError arguments are automatically scrubbed for sensitive data using the same scrubber rules as HTTP request data. Use :scrubber config to customize which Plug.Conn.private keys are retained.
Environment Variables
Variable
Maps to
Purpose
SENTRY_DSN
:dsn
Data Source Name
SENTRY_RELEASE
:release
App version (e.g., my-app@1.0.0)
SENTRY_ENVIRONMENT
:environment_name
Deployment environment
Verification
Test that Sentry is receiving events:
bash
# Send a test event from your project
MIX_ENV=dev mix sentry.send_test_event
Or add a temporary call in a controller action:
elixir
# Temporary test — remove after confirming
def index(conn, _params) do
Sentry.capture_message("Sentry Elixir SDK test event")
text(conn, "sent")
end
Check the Sentry dashboard within a few seconds. If nothing appears:
Set config :sentry, log_level: :debug for verbose SDK output
Verify SENTRY_DSN is set and the project exists
Confirm :environment_name is not set to a value Sentry filters in your alert rules
Phase 4: Cross-Link
After completing Elixir setup, check for a companion frontend missing Sentry coverage:
Connecting Phoenix backend and JavaScript frontend with linked Sentry projects enables distributed tracing — stack traces that span the browser, Phoenix HTTP server, and downstream services in a single trace view.
Troubleshooting
Issue
Solution
Events not appearing
Verify SENTRY_DSN is set; run mix sentry.send_test_event; set log_level: :debug
Missing stack traces on captured exceptions
Pass stacktrace: __STACKTRACE__ in the rescue block: Sentry.capture_exception(e, stacktrace: __STACKTRACE__)
PlugCapture not working on Bandit
Sentry.PlugCapture is Cowboy-only; with Bandit errors surface via LoggerHandler
Source code context missing in production
Run mix sentry.package_source_code before building your OTP release
Context not appearing on async events
Sentry.Context.* is process-scoped; pass values explicitly or propagate Logger metadata across processes
Oban integration not reporting crons
Requires Oban v2.17.6+ or Oban Pro; cron jobs must have "cron" => true in job meta
Duplicate events from Cowboy/Bandit crashes
Set excluded_domains: [:cowboy, :bandit] in LoggerHandler config (both excluded by default as of v13.1.0)
finch not starting
Ensure {:finch, "~> 0.21"} is in deps; Finch is the default HTTP client since v12.0.0
JSON encoding error
Add {:jason, "~> 1.4"} and set json_library: Jason for Elixir < 1.18
Sentry Elixir SDK next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Sentry Elixir SDK compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Sentry Elixir SDK this skillgetsentry/sentry-for-ai
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover.
Answers questions about agent spend, token use, traces, events, errors and tool usage by running read-only SQL against a local TMA1 observability store.
Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and…
Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.
Full Sentry SDK setup for Elixir. An agent skill from getsentry/sentry-for-ai. Sentry Elixir SDK is an agent skill from getsentry/sentry-for-ai, published by the product's own GitHub organization. Full Sentry SDK setup for Elixir.
When should I use Sentry Elixir SDK?
Sentry Elixir SDK fits situations like: asked to add Sentry to Elixir; install sentry for Elixir; configure error monitoring; crons for Elixir.
How do I install Sentry Elixir SDK in Claude Code?
Run `npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a claude-code`. Or copy the skill folder (skills-legacy/sentry-elixir-sdk in getsentry/sentry-for-ai) into .claude/skills/sentry-elixir-sdk in your project. Claude Code loads it when a task matches its description.
How do I install Sentry Elixir SDK in Codex?
Run `npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a codex`. Or copy the skill folder (skills-legacy/sentry-elixir-sdk in getsentry/sentry-for-ai) into .agents/skills/sentry-elixir-sdk in your project. Codex loads it when a task matches its description.
Can I use Sentry Elixir SDK in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add getsentry/sentry-for-ai --skill sentry-elixir-sdk -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sentry-elixir-sdk, .gemini/skills/sentry-elixir-sdk, .github/skills/sentry-elixir-sdk and .opencode/skills/sentry-elixir-sdk in your project.
What does Sentry Elixir SDK need to run?
SKILL.md names no scripts, command-line tools or credentials: Sentry Elixir SDK is instructions for the agent only.
Does Sentry Elixir SDK access the network?
SKILL.md names 1 domain. As links in the text: docs.sentry.io. This is read from the text; nothing was executed.
Is Sentry Elixir SDK safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Sentry Elixir SDK use?
Sentry Elixir SDK is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sentry Elixir SDK use?
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.6k tokens, read only when the agent opens those files.
What are the alternatives to Sentry Elixir SDK?
Skills that share tags, products or a category with Sentry Elixir SDK: Agentsop Observability Setup (agentsope/SkillAlchemy, 457 stars), TMA1 Observability Query (tma1-ai/tma1, 119 stars), Arize Phoenix (Arize-ai/phoenix, 12k stars) and Phoenix Client Development (Arize-ai/phoenix, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sentry Elixir SDK?
getsentry (a GitHub organization, an official publisher) maintains it in getsentry/sentry-for-ai, which has 268 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 7, 2026.
Source: getsentry/sentry-for-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.