fettle: Command for Claude Code

.opencode/commands/fettle-ops-review.md

fettle-ops-review is a command for Claude Code, OpenCode from MilindGaharwar/fettle. It costs 5 tokens per session (1,349 once invoked), scanned A, original, Apache-2.0.

A command for reviewing whether a service is ready to run in production, using a checklist and automated project checks.

In plain words
What is it for?
Use it to inspect service files, container configuration, and other operational indicators, then create a Fettle review document.
Why use it?
It gathers deployment and operations evidence so readiness gaps are easier to find before release.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/.

This is MilindGaharwar/fettle's own configuration. It tells Claude Code and OpenCode how to work on fettle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fettle configures →

Part of the fettle plugin — 34 commands, 4 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to MilindGaharwar/fettle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MilindGaharwar/fettle/main/.opencode/commands/fettle-ops-review.md
Clone the repo
git clone --depth 1 https://github.com/MilindGaharwar/fettle

Made for: Claude Code, OpenCode.

Or install fettle, the plugin that ships this one along with the rest of its 34 commands, 4 hooks.

Wrote 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.

agentmods badge for fettle-ops-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/milindgaharwar/fettle/fettle-ops-review.svg)](https://agentmods.dev/commands/milindgaharwar/fettle/fettle-ops-review)
Your own site
<a href="https://agentmods.dev/commands/milindgaharwar/fettle/fettle-ops-review"><img src="https://agentmods.dev/badge/commands/milindgaharwar/fettle/fettle-ops-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00005 $0.01349
Opus 5 $0.00003 $0.00674
Sonnet 5 $0.00001 $0.00270
Haiku 4.5 $0.00001 $0.00135

Measured 8d ago against content hash 50ceac506603, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fettle-ops-review 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.opencode/commands/fettle-ops-review.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ARGUMENTS refers to any text the user typed after the slash command.

Run a Production Readiness Review (PRR) checklist for the target service.

Procedure

  1. Determine service name. Use $ARGUMENTS if provided. If not provided, derive the name from the current working directory basename.

  2. Create output directory. Create .fettle/ in the current working directory if it doesn't already exist:

    mkdir -p .fettle
    
  3. Copy the ops-review template. Locate the bundled template and write it to .fettle/ops-review-{name}.md, replacing {SERVICE_NAME} with the service name and {DATE} with today's date:

    python3 -c "from fettle._resources import templates_dir; print(templates_dir() / 'ops-review.md')"
    

    Read the file at the printed path.

  4. Run automated checks on the codebase. Use Grep and Glob to scan for operational readiness indicators and pre-fill the template sections:

    Deployment (Section 1):

    • Search for systemd service files: Glob for *.service files in the project or /etc/systemd/.
    • Search for Docker configs: Glob for Dockerfile, docker-compose.yml, docker-compose.yaml, compose.yml, compose.yaml.
    • Search for SIGTERM, signal.signal, signal_handler, GracefulExit, shutdown patterns in Python files.
    • Search for hardcoded secrets: patterns like password=, api_key=, secret= followed by string literals (not env var lookups).
    • If service file or Docker config found, mark deployment item as [PASS]. Otherwise [FAIL].
    • If graceful shutdown handling found, mark that item as [PASS]. Otherwise [?].
    • If hardcoded secrets found, mark secrets item as [FAIL] with file:line. Otherwise [PASS].

    Monitoring (Section 2):

    • Search for health check patterns: health, heartbeat, ping, /healthz, /health in route definitions or scripts.
    • Search for watchdog patterns: watchdog, WatchdogSec, sd_notify, systemd.watchdog.
    • If health check found, mark as [PASS]. Otherwise [FAIL].
    • If watchdog found, mark as [PASS]. Otherwise [?].

    Alerting (Section 3):

    • Search for alerting/notification patterns: telegram, slack, send_message, smtp, email, alert, notify, webhook in source files.
    • If notification mechanism found, mark as [PASS] with details. Otherwise [FAIL].
    • Mark dedup/severity and escalation items as [?] for manual review.

    Resilience (Section 4):

    • Search for timeout patterns: httpx.Timeout, timeout=, socket.settimeout, aiohttp.*timeout, requests.*timeout.
    • Search for retry patterns: tenacity, @retry, backoff, retry_on, max_retries, Retry(.
    • Search for circuit breaker patterns: circuit_breaker, CircuitBreaker, pybreaker.
    • If timeouts found, mark timeout item as [PASS]. Otherwise [FAIL].
    • If retry with backoff found, mark retry item as [PASS]. Otherwise [FAIL].
    • If circuit breaker found, mark as [PASS]. Otherwise [?].

    Data Safety (Section 5):

    • Search for backup patterns: backup, dump, pg_dump, sqlite3 .backup, shutil.copy.
    • Search for atomic write patterns: tempfile, os.rename, os.replace, Path.replace.
    • If backup mechanism found, mark as [PASS]. Otherwise [?].
    • If atomic writes found, mark as [PASS]. Otherwise [?].

    Capacity (Section 6):

    • Search for resource limit patterns: ulimit, MemoryLimit, LimitNOFILE, --memory, mem_limit.
    • Search for log rotation: RotatingFileHandler, TimedRotatingFileHandler, logrotate, maxBytes.
    • If log rotation found, mark as [PASS]. Otherwise [FAIL].
    • Mark remaining items as [?].

    Security (Section 7):

    • Search for secrets in source: hardcoded API keys, passwords, tokens (string literals assigned to variables named key, secret, password, token).
    • Search for os.getenv or environ for secret loading (good practice).
    • Search for input validation: pydantic, validator, validate, sanitize.
    • If secrets loaded from env, mark as [PASS]. If hardcoded, mark as [FAIL] with file:line.
    • If input validation found, mark as [PASS]. Otherwise [?].

Read the full file on GitHub · 97 lines

Changes

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.

  1. 8d ago First seen · 97 lines · 5 tokens per session scan A 50ceac506603

Subscribe to this mod's changes

fettle-ops-review is a command published in the GitHub repository MilindGaharwar/fettle (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 5 tokens to every session and 1,349 once invoked, about $0.0000 per session on Opus 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 2026-08-31.