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/resolve-pr-comments-stack/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/resolve-pr-comments-stack)<a href="https://agentmods.dev/skills/maximhq/bifrost/resolve-pr-comments-stack"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/resolve-pr-comments-stack/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/resolve-pr-comments-stack"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/resolve-pr-comments-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 284 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 298 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.05175 |
| Opus 5.5 | $0.00040 | $0.02070 |
| Sonnet 5.5 | $0.00020 | $0.01035 |
| Haiku 4.5 | $0.00010 | $0.00517 |
Grade A, and why
resolve-pr-comments-stack 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve PR Comments — Stack
Systematically resolve unresolved review comments (CodeRabbit, Greptile, human reviewers)
across every branch in a Graphite stack, working bottom-up in a single checkout. Each
branch's fixes are committed into that branch via gt modify before moving to the next,
so the stack stays restacked and consistent throughout — no branch is left dirty, and no
branch is worked on out of dependency order. Nothing in this pass changes the user's tree
or branches without their say-so: every code edit and reply is approved per comment, and
every gt modify (or gt restack) is approved per branch, before it runs.
This is the stack-wide orchestration layer. The per-PR triage logic (fetch threads,
classify FIX/REPLY/SKIP, apply) is the same as the single-PR resolve-pr-comments skill;
this skill adds the ordering, persistence, and cross-branch judgment on top.
When to reach for this vs. the single-PR skill
Use this skill when the target is a stack — a list of PR numbers with dependency order,
or "go through this whole thing". Use the plain resolve-pr-comments skill for a single,
standalone PR. A stack pass invokes the single-PR triage logic once per branch internally;
it does not require calling that skill separately.
Step 0: Establish stack order and confirm working mode
Get the real dependency order, don't trust an externally supplied list blindly:
gt log --stack
Cross-reference against whatever PR list was given. Confirm with the user (AskUserQuestion)
only if genuinely ambiguous — e.g., the given list doesn't obviously map onto one contiguous
run of the stack, or ordering conflicts with what gt log shows. Otherwise proceed bottom-up
(base branches first): a later branch's design routinely supersedes an earlier one's, and
working bottom-up means each branch is fixed before its descendants are even touched.
Work serially, in place, in one working directory — checkout each branch in turn, never use worktrees for this. Multi-branch work with a shared identity (this same PR-comment pass) belongs in one checkout, not parallel worktrees.
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 Changed · +30 lines eaed1c59cae9
- 1mo ago First seen · 340 lines · 99 tokens per session scan A 241b2d1ff770
resolve-pr-comments-stack is a skill published in the GitHub repository maximhq/bifrost (8,898 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 5,175 once invoked, about $0.0004 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.
github
GitHub PR and issue workflows via gh CLI — read-only by default; merge requires approval.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.