Caveman Gateway Setup
JuliusBrussee/caveman
Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.
Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.
Install Production Readiness
$ npx skills add KbWen/agentic-os --skill production-readiness -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install KbWen/agentic-os production-readiness --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/KbWen/agentic-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/production-readiness .claude/skills/production-readiness && 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 "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .claude/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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/KbWen/agentic-os/tree/main/.agents/skills/production-readinessType 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 KbWen/agentic-os --skill production-readiness -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install KbWen/agentic-os production-readiness --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KbWen/agentic-os.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/production-readiness .agents/skills/production-readiness && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .agents/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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 KbWen/agentic-os --skill production-readiness -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install KbWen/agentic-os production-readiness --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KbWen/agentic-os.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/production-readiness .cursor/skills/production-readiness && 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 "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .cursor/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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/KbWen/agentic-os.git --path .agents/skills/production-readiness--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 KbWen/agentic-os --skill production-readiness -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install KbWen/agentic-os production-readiness --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KbWen/agentic-os.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/production-readiness .gemini/skills/production-readiness && 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 "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .gemini/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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 KbWen/agentic-os production-readinessInstalls 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 KbWen/agentic-os --skill production-readiness -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/KbWen/agentic-os.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/production-readiness .github/skills/production-readiness && 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 "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .github/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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 KbWen/agentic-os --skill production-readiness -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install KbWen/agentic-os production-readiness --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KbWen/agentic-os.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/production-readiness .opencode/skills/production-readiness && 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 "production-readiness" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/production-readiness into .opencode/skills/production-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "production-readiness", 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
production-readiness- GitHub stars
- 207
- Token cost
- ~938 tokens
- SKILL.md length
- 395 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.
- Works in 3 steps: Error Surface Audit (at /review) → Log Sink Documentation (at /ship) → Rollback Telemetry (at /ship)
- Tasks that involve Observability
- SKILL.md covers Overview, When to Use, Observability Checklist and Heading-Scoped Read Note, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Production Readiness is an agent skill from KbWen/agentic-os. Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.
Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in DevOps & Cloud, covering Observability. The repository describes itself as: Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in… The licence is MIT.
When your agent uses it
- Tasks that involve Observability
Example prompts
- “/production-readiness”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 81a4034. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 Readiness loads about 938 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 395 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
The full file from KbWen/agentic-os at commit 81a4034, republished under its MIT licence (© KbWen). 395 words, ~938 tokens.
Download SKILL.mdSave it as
.claude/skills/production-readiness/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- production-readiness
- description
- Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.
Production Readiness
Overview
Code that passes all tests but logs errors only via debug-only APIs (e.g., debugPrint, console.log in debug mode) is functionally silent in production. This skill enforces observability readiness before ship — ensuring the team is not blind during beta testing and production rollout.
When to Use
- Auto-recommended for
featureandarchitecture-changeclassifications. - Activate manually when working on error handling, crash reporting, or logging infrastructure.
- Apply at
/review(semantic error check) and/ship(readiness checklist).
Observability Checklist
1. Error Surface Audit (at /review)
For every catch / error-handling block in changed files:
| Check | Pass | Fail |
|---|---|---|
| Logging call exists | Logger.error(), log.error(), crashReporter.capture() | Empty catch {} |
| Logger is production-observable | Framework logger, crash reporter, structured stdout | debugPrint(), print(), debug-only console.log |
| Error context is actionable | Includes error type, operation, identifiers | "error occurred", raw exception only |
2. Log Sink Documentation (at /ship)
Document in Work Log where production errors go:
## Observability
- Error sink: [e.g., Sentry via Logger.error(), Crashlytics, stdout → CloudWatch]
- Health check: [e.g., /health endpoint, Firebase Vitals, uptime monitor]
- Rollback signal: [e.g., error rate > 2x baseline → revert]If the project has no production logging infrastructure, document as Known Risk:
"No production error reporting configured. Errors in catch blocks will be logged to stdout only. Risk: silent failures in release builds if stdout is not monitored."
3. Rollback Telemetry (at /ship)
The rollback plan (per engineering_guardrails.md §12.5) must answer:
- How will operators know the rollback is needed? (alert, dashboard, manual check)
- How will operators know the rollback succeeded? (error rate drops, health check passes)
Heading-Scoped Read Note
For phase-entry loading, read only:
When to UseObservability Checklist
Load What This Skill Does NOT Cover, Anti-Patterns, and Interaction with Other Skills on full read or cache miss only.
Show full SKILL.md (142 more words)Show less
What This Skill Does NOT Cover
- Tool selection: Sentry vs Crashlytics vs Datadog — team/project decides.
- Alert thresholds: When to page on-call — SRE/ops owns this.
- Dashboards: What to visualize — team preference.
- Post-deploy monitoring: This is a pre-ship readiness check, not an ops workflow.
Anti-Patterns
| Anti-Pattern | Why It Fails | Fix |
|---|---|---|
catch (e) { debugPrint(e); } | Tree-shaken in release build | Use production logger |
catch (e) { /* TODO: add logging */ } | Silent catch escapes review | Add logging now, not later |
Logger.error("error") without context | Useless in production triage | Include operation, identifiers, error type |
| Logging to local file only | Not observable in cloud/mobile | Use centralized error reporting |
Interaction with Other Skills
- systematic-debugging: Complements — debugging finds bugs, production-readiness ensures they're visible when they happen again.
- verification-before-completion: Works alongside — verification checks correctness, production-readiness checks observability.
- auth-security: Security errors are especially critical to observe in production. §5.2a applies with elevated priority to auth error paths.
© KbWen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/production-readiness of KbWen/agentic-os.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 81a4034
Compare with similar skills
Production Readiness 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 Readiness this skillKbWen/agentic-os | 207 | — | ~938 | Automated safety check: Pass | MIT | |
| Caveman Gateway SetupJuliusBrussee/caveman | 111k | 1 repos | ~2.6k | Automated safety check: Warn | Apache-2.0 | |
| Agent Kill Switchvivekchand/clawmetry | 426 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Sls Dashboard Builderalibaba/loongsuite-pilot | 201 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Clawmetry Selfcheckvivekchand/clawmetry | 426 | — | ~515 | Automated safety check: Pass | MIT | |
| Improve PromptAgentX-ai/AgentX-Trace-Eval | 106 | — | ~2k | Automated safety check: Pass | Custom licence |
Similar skills
Agent Kill Switch
vivekchand/clawmetry
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.
Sls Dashboard Builder
alibaba/loongsuite-pilot
当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用；尤其适用于线上大盘、强对比的分析看板、已校验的查询包，或需要专业中文标签与指标定义的运维向大盘。
Clawmetry Selfcheck
vivekchand/clawmetry
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.
Improve Prompt
AgentX-ai/AgentX-Trace-Eval
Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…
- Official
Agent Platform Alert Configuration
google/skills
Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.
More from KbWen/agentic-os
All 12 skills in this repoAPI Design
KbWen/agentic-os
Design or review REST/GraphQL APIs when endpoints or contracts change.
Frontend Patterns
KbWen/agentic-os
Apply frontend conventions when components, pages, forms, or client state change.
Karpathy Principles
KbWen/agentic-os
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
Doc Lookup
KbWen/agentic-os
Check official docs when framework APIs or configuration may be version-sensitive.
Systematic Debugging
KbWen/agentic-os
A skill your agent uses when investigating a bug, test failure, flaky test, unexpected behavior, or a hotfix, or an unexplained or failed fix; find the root cause first.
Database Design
KbWen/agentic-os
Design schemas and migrations when persistent data structures change.
Related
Categories
Questions about Production Readiness
What does Production Readiness do?
Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring. Production Readiness is an agent skill from KbWen/agentic-os. Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.
When should I use Production Readiness?
Production Readiness fits situations like: tasks that involve Observability.
How do I install Production Readiness in Claude Code?
Run `npx skills add KbWen/agentic-os --skill production-readiness -a claude-code`. Or copy the skill folder (.agents/skills/production-readiness in KbWen/agentic-os) into .claude/skills/production-readiness in your project. Claude Code loads it when a task matches its description.
How do I install Production Readiness in Codex?
Run `npx skills add KbWen/agentic-os --skill production-readiness -a codex`. Or copy the skill folder (.agents/skills/production-readiness in KbWen/agentic-os) into .agents/skills/production-readiness in your project. Codex loads it when a task matches its description.
Can I use Production Readiness 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 KbWen/agentic-os --skill production-readiness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/production-readiness, .gemini/skills/production-readiness, .github/skills/production-readiness and .opencode/skills/production-readiness in your project.
What does Production Readiness need to run?
SKILL.md names no scripts, command-line tools or credentials: Production Readiness is instructions for the agent only.
Does Production Readiness access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Production Readiness 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 Readiness use?
Production Readiness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Production Readiness use?
About 938 tokens (SKILL.md is roughly 3.8k 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 Readiness?
Skills that share tags, products or a category with Production Readiness: Caveman Gateway Setup (JuliusBrussee/caveman, 111k stars), Agent Kill Switch (vivekchand/clawmetry, 426 stars), Sls Dashboard Builder (alibaba/loongsuite-pilot, 201 stars) and Clawmetry Selfcheck (vivekchand/clawmetry, 426 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Production Readiness?
KbWen (a GitHub user) maintains it in KbWen/agentic-os, which has 207 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 6, 2026.
Source: KbWen/agentic-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.