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/stack-absorb/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/stack-absorb)<a href="https://agentmods.dev/skills/maximhq/bifrost/stack-absorb"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/stack-absorb/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/stack-absorb"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/stack-absorb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 102 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00125 | $0.02536 |
| Opus 5.5 | $0.00050 | $0.01014 |
| Sonnet 5.5 | $0.00025 | $0.00507 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
stack-absorb 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Absorb
Distribute a set of changes across the correct commits in a Graphite stack, by hand,
when gt absorb's blame-based algorithm won't produce a clean result. This is slower
than gt absorb -f but gives a coherent, reviewable history: each target branch gets
exactly the hunks that belong to it, described in its own commit message, with nothing
stray swept in.
When to reach for this vs. plain gt absorb
Check git status --short first. Untracked (??) files are never absorbed even with
gt absorb -a - that flag only stages unstaged tracked changes, file creations are
never picked up. If any untracked files are part of the intended change, treat them as
part of the manual split below rather than expecting the dry-run to cover them.
Then try gt absorb -a --dry-run first - it's free and sometimes it's exactly right.
Read its output critically:
- If every hunk absorbs into a commit that's a good semantic fit, there's no
significant "Not absorbed" leftover, and no untracked files were left out of
consideration, just run
gt absorb -a -f(or let the user run it) and stop here. - If it scatters hunks across commits that are a poor conceptual fit (a stale
docs-sync commit, a commit about a different concern that happens to touch the same
lines), or leaves substantial new code as "Not absorbed" (no prior line to blame
onto - new functions, new JSX blocks, new state), that's the signal to do this
manually. Tell the user what
gt absorb --dry-runwould do and why it's messier than a hand split, and confirm before proceeding (AskUserQuestion) - this is a judgment call about commit history shape, not a mechanical one.
Step 1: Map every change to its target branch
For each distinct concern in the diff, find the commit that should own it:
git log --oneline -S"<distinctive string from the change>" --all -- "<file>"
Pick a string that's specific to the concept being changed (a function name, a UI
label, an error message), not boilerplate. The oldest/most relevant match is usually
the commit that introduced what you're now modifying. Then resolve that commit to a
current branch tip - git branch --contains alone is not the answer, only a candidate
list: in a stacked history every branch above the true owner also contains that
commit, since it's in their ancestry too.
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.
- 1mo ago First seen · 200 lines · 125 tokens per session scan A 6be35192e9aa
stack-absorb is a skill published in the GitHub repository maximhq/bifrost (8,898 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 2,536 once invoked, about $0.0005 per session on Opus 5.5. 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
merge-prs
Consume analyzed PR plans, implement authorized fixes with contributor credit, validate exact candidates, and merge only owner-selected and explicitly authorized groups through the shared gates. Requires prior review evidence; unknown or failing required checks remain HOLD.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
maintainer-ops
Use for vLLM Semantic Router issue intake, PR decisions, releases, and reviewed GitHub mutations performed on behalf of maintainers.
release-notes
Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.