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.
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.
curl -O https://raw.githubusercontent.com/maximhq/bifrost/dev/.claude/skills/changelog-writer/SKILL.mdgit clone --depth 1 https://github.com/maximhq/bifrostWrote 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.
[](https://agentmods.dev/skills/maximhq/bifrost/changelog-writer)<a href="https://agentmods.dev/skills/maximhq/bifrost/changelog-writer"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/changelog-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maximhq/bifrost/changelog-writer"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/changelog-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.05460 |
| Opus 5 | $0.00036 | $0.02730 |
| Sonnet 5 | $0.00015 | $0.01092 |
| Haiku 4.5 | $0.00007 | $0.00546 |
Grade A, and why
changelog-writer 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog Writer
Generate changelogs for a new Bifrost release. Reads git history to identify changes per module, asks the user for version bump type, bumps all module versions respecting the dependency hierarchy, writes transports/changelog.md and per-module changelog.md files, and updates version files.
IMPORTANT: This skill NEVER creates or modifies files under docs/. No MDX files, no docs.json updates. Only changelog.md and version files within module directories.
Module Hierarchy
Changes cascade down this dependency chain:
core → framework → plugins → transports
- core depends on nothing internal
- framework depends on core
- plugins/* each depend on core + framework
- transports depends on core + framework + all plugins
If core changes, every module below it must bump its version (at minimum a patch bump).
If framework changes (but not core), plugins and transports must bump.
If only a plugin changes, transports must bump.
If only transports changes, only transports bumps.
Usage
/changelog-writer # Interactive - prompts for everything
/changelog-writer <transport-ver> # Pre-set transport version (e.g., v1.5.0)
Workflow
Step 1: Gather Current State
Read the current version of every module:
echo "core: $(cat core/version)"
echo "framework: $(cat framework/version)"
echo "transports: $(cat transports/version)"
for d in plugins/*/; do echo "$(basename $d): $(cat ${d}version)"; done
To understand the previous release state, use the latest released tags (do NOT use docs/changelogs file mtimes - that directory also holds helm-, cli-, edge-, ent-, and prerelease files):
for prefix in core framework transports; do
git tag -l "$prefix/v*" --sort=-v:refname | head -1
done
If a docs changelog for that transport version exists (docs/changelogs/v<version>.mdx), read it to know the previous versions of all modules.
Step 2: Identify Changes Since Last Release
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.
- 13d ago First seen · 462 lines · 73 tokens per session scan A 5ac7b779193a
changelog-writer is a skill published in the GitHub repository maximhq/bifrost (7,987 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 5,460 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.
Other skills, from other repositories
release-management
Tag a commit, publish a GitHub release, and read, correct or withdraw the tags and releases already there.
hmem-release
Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.
new-project
Bootstrap a new product repository for agentic development. Use when starting a new app, empty repo, greenfield project, or when the user asks to stand up the factory, the start loop, or what to install before the first feature.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.