Axiom SRE Investigator
openclaw/clawhub
Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.
Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report.
Install Production Error Hunt
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install different-ai/openwork hunt-a-prod-error --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .claude/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .claude/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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.
$skill-installer install https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-errorType 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.
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install different-ai/openwork hunt-a-prod-error --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .agents/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .agents/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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.
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install different-ai/openwork hunt-a-prod-error --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .cursor/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .cursor/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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.
$ gemini skills install https://github.com/different-ai/openwork.git --path .opencode/skills/hunt-a-prod-error--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install different-ai/openwork hunt-a-prod-error --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .gemini/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .gemini/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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.
$ gh skill install different-ai/openwork hunt-a-prod-errorInstalls 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).
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .github/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .github/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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.
$ npx skills add different-ai/openwork --skill hunt-a-prod-error -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install different-ai/openwork hunt-a-prod-error --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/hunt-a-prod-error .opencode/skills/hunt-a-prod-error && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hunt-a-prod-error" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/hunt-a-prod-error into .opencode/skills/hunt-a-prod-error/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt-a-prod-error", 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
hunt-a-prod-error- GitHub stars
- 24k
- Token cost
- ~803 tokens
- SKILL.md length
- 347 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report.
- Works in 5 steps: Local logs: where and how often → Sentry: what threw → Name the regression → …
- A user reports internal_error, a 500 or Unexpected server error in a shipped build
- SKILL.md covers 1. Local logs: where and how…, 2. Sentry: what threw, 3. Name the regression and 4. Reproduce on the shipping…, plus 1 more section
- Calls rg, python3 and npx; reaches us.sentry.io
What it does
An opaque error has two halves, and the skill insists on both. Local logs say where and how often: the desktop server log (OTLP JSON, one record per request) and the engine log, with 5xx responses tallied by route and compared with sibling routes that did not fail. Sentry says what threw: the agent searches issues through OpenWork Connect, filters by `surface:server`, the templated `route` and `release`, and reads the stack, first-seen time, users and event count.
Next it correlates the first-seen time with recent git history on the files in the stack, confirms the shipped code matches source, and reproduces the mechanism on the runtime where the error happened, since a repro on a different runtime proves nothing. Finally it files an issue in Linear with the user-facing string, route tally, Sentry issue IDs, mechanism, repro, regressing PR and a proposed fix, and replies where the report came from. One caveat noted is that proxy catch blocks send the real exception only to Sentry.
When your agent uses it
- A user reports internal_error, a 500 or Unexpected server error in a shipped build
- Matching a Sentry issue to the pull request that introduced it
- Tallying 5xx errors by route in server logs
Example prompts
- “A user hit Unexpected server error in the desktop app, so find the cause and file it.”
- “Tally 5xx by route in the OpenWork server log and compare against the routes that worked.”
- “Which PR introduced the new Sentry issue on the workspace opencode route?”
Requirements
- Access to OpenWork's local server and engine logs
- Sentry connected through OpenWork Connect
- A Linear workspace for filing the issue
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Local logs: where and how often
- Sentry: what threw
- Name the regression
- Reproduce on the shipping runtime
- File and reply
What it can do on your machine
Read from SKILL.md and the folder at commit 9ce20f8. 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
Shell commands in SKILL.md call:
rgpython3npxgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
us.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
Production Error Hunt loads about 803 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 347 words of instructions outside code blocks.
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.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 347 words (~803 tokens).
“An opaque error has two halves. Local logs say where (route, status, timing, burst shape). Sentry says what (the exception and stack). You need both before naming a cause; either alone produces a guess.”
- name
- hunt-a-prod-error
Files
Just SKILL.md in .opencode/skills/hunt-a-prod-error of different-ai/openwork.
Open the folder on GitHubat commit 9ce20f8
Compare with similar skills
Production Error Hunt 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Production Error Hunt this skilldifferent-ai/openwork | 24k | — | ~803 | Automated safety check: Pass | Custom licence | |
| Axiom SRE Investigatoropenclaw/clawhub | 9.5k | — | ~7.1k | Automated safety check: Pass | MIT | |
| Code Design Rationale Investigatorcursor/plugins | 10k | 9 repos | ~2.6k | Automated safety check: Pass | None | |
| Debug MasteryxenitV1/claude-code-maestro | 229 | — | ~2.5k | Automated safety check: Notes | MIT | |
| Debugging and Error Recoveryaddyosmani/agent-skills | 103k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Sentry Issue Fix Looptixl3d/tixl | 5.1k | — | ~2.1k | Automated safety check: Notes | MIT |
Similar skills
- Official
Code Design Rationale Investigator
cursor/plugins
Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.
Debug Mastery
xenitV1/claude-code-maestro
Systematic debugging methodology with 4-phase process, root cause tracing, and elite observability standards.
Debugging and Error Recovery
addyosmani/agent-skills
Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.
Sentry Issue Fix Loop
tixl3d/tixl
Walks through open Sentry issues for the tooll3 project, latest first, proposing a fix for each and committing them one at a time with your review between.
Root Cause Tracing
sandgardenhq/sgai
A skill your agent uses when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation…
More from different-ai/openwork
All 33 skills in this repoOpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
Fake Model Provider Faults
different-ai/openwork
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
OpenWork Model Alias Manager
different-ai/openwork
Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
OpenWork Electron Browser Automation
different-ai/openwork
Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.
Daytona Sandbox Operations
different-ai/openwork
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
Related
Categories
Questions about Production Error Hunt
What does Production Error Hunt do?
Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report. An opaque error has two halves, and the skill insists on both. Local logs say where and how often: the desktop server log (OTLP JSON, one record per request) and the engine log, with 5xx responses tallied by route and compared with sibling routes that did not fail.
When should I use Production Error Hunt?
Production Error Hunt fits situations like: A user reports internal_error, a 500 or Unexpected server error in a shipped build; matching a Sentry issue to the pull request that introduced it; tallying 5xx errors by route in server logs.
How do I install Production Error Hunt in Claude Code?
Run `npx skills add different-ai/openwork --skill hunt-a-prod-error -a claude-code`. Or copy the skill folder (.opencode/skills/hunt-a-prod-error in different-ai/openwork) into .claude/skills/hunt-a-prod-error in your project. Claude Code loads it when a task matches its description.
How do I install Production Error Hunt in Codex?
Run `npx skills add different-ai/openwork --skill hunt-a-prod-error -a codex`. Or copy the skill folder (.opencode/skills/hunt-a-prod-error in different-ai/openwork) into .agents/skills/hunt-a-prod-error in your project. Codex loads it when a task matches its description.
Can I use Production Error Hunt 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 different-ai/openwork --skill hunt-a-prod-error -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hunt-a-prod-error, .gemini/skills/hunt-a-prod-error, .github/skills/hunt-a-prod-error and .opencode/skills/hunt-a-prod-error in your project.
What does Production Error Hunt need to run?
Going by SKILL.md and its folder, Production Error Hunt needs the command-line tools its instructions call (rg, python3, npx and git). Our summary lists: Access to OpenWork's local server and engine logs; Sentry connected through OpenWork Connect; A Linear workspace for filing the issue.
Does Production Error Hunt access the network?
SKILL.md names 1 domain. In commands or code: us.sentry.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Production Error Hunt 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 Production Error Hunt use?
Production Error Hunt has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Production Error Hunt use?
About 803 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Production Error Hunt?
Skills that share tags, products or a category with Production Error Hunt: Axiom SRE Investigator (openclaw/clawhub, 9.5k stars), Code Design Rationale Investigator (cursor/plugins, 10k stars), Debug Mastery (xenitV1/claude-code-maestro, 229 stars) and Debugging and Error Recovery (addyosmani/agent-skills, 103k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Production Error Hunt?
different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,943 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 8, 2026.
Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.