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/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)<a href="https://agentmods.dev/skills/maximhq/bifrost/resolve-pr-comments"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/resolve-pr-comments/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"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/resolve-pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 295 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 | $0.00000 | $0.03613 |
| Opus 5.5 | $0.00000 | $0.01445 |
| Sonnet 5.5 | $0.00000 | $0.00723 |
| Haiku 4.5 | $0.00000 | $0.00361 |
Grade A, and why
resolve-pr-comments 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: resolve-pr-comments description: Resolve all unresolved PR comments interactively. Makes local edits only—NEVER commits or pushes. Use when asked to resolve PR comments, address review feedback, handle CodeRabbit comments, or fix PR review issues. Invoked with /resolve-pr-comments <PR_NUMBER> or /resolve-pr-comments <owner/repo> <PR_NUMBER>. allowed-tools: Read, Grep, Glob, Bash, Edit, Write, WebFetch, Task, AskUserQuestion, TodoWrite
Resolve PR Comments
An interactive workflow to systematically address all unresolved PR review comments.
Usage
/resolve-pr-comments <PR_NUMBER>
/resolve-pr-comments <owner/repo> <PR_NUMBER>
If no repo is specified, uses the current git repository's remote origin.
Before starting the workflow - if the flow is in Plan Model - ask if the user wants to move to default mode to solve the comments one by one. Mention that each PR resolve has planning attached to it.
Workflow Overview
- Detect repository - Get owner/repo from git remote or user input
- Fetch unresolved comments - Use GitHub GraphQL API (REST doesn't expose resolved status). Paginate through
reviewThreads(cursor-based) so all pages are checked when a PR has more than 100 threads. - Create tracking file - Maintain state across the session
- For each comment:
- Get full details and any existing replies
- Show the diff view of existing code in a proper diff view
- Before suggesting the fix - do the research via documentations. And present all that docs research and relevant links to the user with the fix. Use context 7. MAKE SURE YOU DO THIS ALWAYS
- Present to user with options (FIX, REPLY, SKIP)
- Wait for user decision
- Execute the action
- Update tracking
- Verify resolution - Check remaining unresolved count
- Repeat until done - Continue until all comments resolved
Step 1: Detect Repository
If repository not provided, detect from git remote:
git remote get-url origin | sed -E 's|.*github.com[:/]([^/]+/[^/.]+)(\.git)?|\1|'
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 b84f5a1b94f1
- 1mo ago Changed · +36 lines adf499556e49
- 2mo ago First seen · 306 lines · 0 tokens per session scan A 753fea0e7b03
resolve-pr-comments is a skill published in the GitHub repository maximhq/bifrost (9,185 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,613 tokens. 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.
green-prs
Inspect and prepare the selected PR queue against its exact current base, repair authorized defects with contributor credit, and report full versus partial validation. Use for maintainer pre-greening; merging requires separate owner authorization and the shared merge gates.
pr-review
Review a GitHub pull request using multiple expert personas. Takes a PR URL as input, analyzes the changes, and generates comprehensive review feedback from different perspectives (Merge Specialist, Frontend, Backend, Security, DevOps, AI/Agent, SRE, Chief Architect).
unrelated-tools
Search, inspect, and call tools exposed through an Unrelated MCP Gateway profile using the unrelated CLI. Use when a task may be handled by an authorized Gateway tool, when the exact tool name or input schema is unknown, or when a compact client-side alternative to loading a full MCP catalog is desired.
unified-ai-gateway
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.