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 skills add tomzx/agents --skill resolve-pr-conflictsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/resolve-pr-conflicts)<a href="https://agentmods.dev/skills/tomzx/agents/resolve-pr-conflicts"><img src="https://agentmods.dev/badge/skills/tomzx/agents/resolve-pr-conflicts/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/tomzx/agents/resolve-pr-conflicts"><img src="https://agentmods.dev/badge/skills/tomzx/agents/resolve-pr-conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 149 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 171 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 149 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 Agent Snooping · line 196 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00115 | $0.04103 |
| Opus 5 | $0.00057 | $0.02051 |
| Sonnet 5 | $0.00023 | $0.00821 |
| Haiku 4.5 | $0.00012 | $0.00410 |
Grade A, and why
resolve-pr-conflicts 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 6d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve PR Conflicts
Finds every open pull request authored by the current user in a repository that has merge conflicts, then resolves each one in parallel. The skill is split into two roles:
- Orchestrator (this session): scans the repo, detects which of the user's PRs have conflicts, prepares one worktree per conflicting PR (reusing an existing one when present), discovers the project's verification commands once, then fans out to one sub-agent session per PR and aggregates the results.
- Sub-agent (one per PR, concurrent): works inside its assigned worktree, merges the base branch, resolves the conflict markers, runs verification, pushes, and posts a comment.
Because the PRs are independent, fixing them in separate concurrent sessions is dramatically faster than sequential resolution. Each sub-agent owns a distinct worktree and a distinct head branch, so there are no filesystem or git-push races.
Designed to be safe to run unattended: ambiguous conflicts and PRs that fail verification are aborted and reported by that PR's sub-agent, never pushed.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. ghCLI authenticated with write access to the target repository (and to the PR head branches)git worktreeavailable- The current git user is the author of the target PRs (
@me) - The current working directory is a checkout of the target repository, or a target repo is passed as
owner/repo - A sub-agent capable of writing code (use the
generalsubagent_type). If sub-agent dispatch is unavailable, fall back to processing PRs sequentially as described in "Fallback: sequential mode". - Read any files present under
.sdlc/context/and apply any artifact style rules found there
Skill attribution (GitHub)
Before posting to GitHub, read ../github-post-attribution/SKILL.md and append the footer for SKILL_DIR = resolve-pr-conflicts. Each sub-agent appends the same footer for its own PR comment.
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.
- 6d ago First seen · 302 lines · 115 tokens per session scan A 6618c216b102
resolve-pr-conflicts is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 4,103 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.