bifrost: Skill for Claude Code

.claude/skills/release-checklist/SKILL.md

release-checklist is a skill for Claude Code from maximhq/bifrost. It costs 82 tokens per session (2,507 once invoked), scanned A, original, Apache-2.0.

A read-only release audit for Bifrost changes, focused on database migrations and application startup. It checks for lock or deadlock risks at scale and work that could delay booting.

In plain words
What is it for?
Use it to review a Git change range before release and produce pass, warning, or failure findings with suggested remedies.
Why use it?
It can reveal release-time database and startup problems before the changes reach users, while keeping the audit itself non-destructive.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

This is maximhq/bifrost's own configuration. It tells Claude Code how to work on bifrost 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 bifrost configures →

About the project

Bifrost is an AI gateway that gives applications one OpenAI-compatible API for accessing models from more than 23 providers. It is used to route model requests, handle provider failover and load balancing, and apply features such as caching, guardrails, and MCP gateway support.

maximhq/bifrost · 7,847 stars · on GitHub · getmaxim.ai

Reuse

Borrowing it

Nothing to install: this file belongs to maximhq/bifrost. 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/maximhq/bifrost/dev/.claude/skills/release-checklist/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/maximhq/bifrost

Made for: Claude Code.

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 release-checklist

README.md
[![agentmods](https://agentmods.dev/badge/skills/maximhq/bifrost/release-checklist.svg)](https://agentmods.dev/skills/maximhq/bifrost/release-checklist)
Your own site
<a href="https://agentmods.dev/skills/maximhq/bifrost/release-checklist"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/release-checklist.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,507 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 $0.00082 $0.02507
Opus 5 $0.00041 $0.01254
Sonnet 5 $0.00016 $0.00501
Haiku 4.5 $0.00008 $0.00251

Measured 7d ago against content hash 8dbe10dd5a28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

release-checklist 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 7d 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.

.claude/skills/release-checklist/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Checklist

A pre-release safety audit. Given a set of changes destined for release, run every check in the Checks Registry below and produce one consolidated report. This skill is read-only: it diagnoses, recommends a concrete fix for every finding, and never edits files. Applying a fix is a separate, explicitly-approved step.

The registry currently holds two migration-safety checks. It is designed to grow - see Adding a New Check.

Scope: what "the release" means

Determine the change set to audit, in this order:

  1. If the user passed a git ref or range (e.g. /release-checklist v1.4.0..HEAD or /release-checklist origin/dev), use it.
  2. Otherwise default to everything not yet on the main branch: diff origin/dev...HEAD (three-dot) and also include uncommitted working-tree changes.
  3. If that range is empty, tell the user and ask for an explicit range.

Gather the raw material once, up front:

git fetch origin --quiet
git diff --stat origin/dev...HEAD
git diff origin/dev...HEAD -- '**/migrations.go' '**/matviews.go'
git status --porcelain

Migrations here are Go-defined, not .sql files. They live in:

  • framework/configstore/migrations.go - config DB (providers, keys, virtual keys, budgets)
  • framework/logstore/migrations.go - log DB (request logs; the high-volume table)
  • framework/logstore/matviews.go - materialized views over the log DB

A release with no diff in these files has no migration risk - record both migration checks as PASS (no migrations changed) and move on.

Migration system facts (needed by both checks)

  • All migrations run synchronously at boot. triggerMigrations() executes the full ordered migration list during store init, before the process serves traffic.
  • Supported databases: PostgreSQL and SQLite only. No MySQL. Lock behavior differs sharply between the two - judge both.
  • Migrations are cluster-serialized behind Postgres advisory lock 1000001 with a 5-minute acquisition timeout. A slow migration on one pod stalls every other pod's boot.
  • Each migration func runs in a transaction by default (Options.UseTransaction = true). A transaction holds every lock until the func returns - migration duration is lock duration.
  • Established escape hatch for heavy work: index builds and materialized views run in post-startup background goroutines under separate advisory locks (1000002 for indexes, 1000005/1000006 for matviews) - see framework/logstore/postgres.go, ensurePerformanceIndexes(), ensureMatViews(). migrationAddProviderHistogramIndex is intentionally a near-no-op that defers the real CREATE INDEX CONCURRENTLY there. This deferral pattern is the correct fix for anything heavy.

Read the full file on GitHub · 194 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. 7d ago First seen · 194 lines · 82 tokens per session scan A 8dbe10dd5a28

Subscribe to this mod's changes

release-checklist is a skill published in the GitHub repository maximhq/bifrost (7,847 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 2,507 once invoked, about $0.0004 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 2026-08-30.