Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/maximhq/bifrost/resolve-pr-comments-stacknpx skills add maximhq/bifrost --skill resolve-pr-comments-stackgit 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.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00099 | $0.05175 |
| Opus 5 | $0.00049 | $0.02587 |
| Sonnet 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 yesterday.
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.
- yesterday Changed · +30 lines eaed1c59cae9
- 4d 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 (7,783 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 5,175 once invoked, about $0.0005 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
eclipse-debug
Debug Java applications in Eclipse — set breakpoints, launch in debug mode, step through code, inspect stack traces, evaluate expressions, and hot-swap code changes.
eclipse-test
Run JUnit tests in Eclipse projects — all tests, by package, by class, or individual test methods. Also build Maven projects.
eclipse-run
Launch and stop Java applications in Eclipse. Run with program/VM arguments, capture stdout/stderr, or launch in background.
eclipse-analyze
Analyze Java code using Eclipse JDT tools — type hierarchy, find references, call hierarchy, compilation errors, quick fixes, and import suggestions. Use this to understand code structure before making changes.
release-alignment
Use this skill for MCPMate pre-release or post-release documentation alignment, including GitHub Release Notes, website changelog entries, README release-facing copy, roadmap positioning, localized website docs, and release-description/changelog consistency checks.
uat-acceptance
Use this skill for MCPMate UI/UX review, UAT planning, Playwright acceptance, Admin Console acceptance, Board acceptance, Extension delivery acceptance, or any request to judge whether a page, flow, component, PR, or deliverable conforms to MCPMate product taste and acceptance standards. Use it even when the user does…