Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsnpx agentmods add skills/rjmurillo/ai-agents/merge-resolverWrote 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/rjmurillo/ai-agents/merge-resolver)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/merge-resolver"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/merge-resolver/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/rjmurillo/ai-agents/merge-resolver"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/merge-resolver.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 MCP Rug Pull · line 81 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 241 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00093 | $0.04084 |
| Opus 5.5 | $0.00037 | $0.01634 |
| Sonnet 5.5 | $0.00019 | $0.00817 |
| Haiku 4.5 | $0.00009 | $0.00408 |
Grade A, and why
merge-resolver scanned grade A with 1 finding 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 19d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| All conflicts resolved | `python3 -c "import subprocess, sys; r=subprocess.run(['git','diff','--name-only','--diff-filter=U'],capture_output=True,text=True,encoding='utf-8',errors='replace'); u=[l for l in r.stdout.spl How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Resolver
Resolve merge conflicts by analyzing git history and commit intent.
Quick Start
# Resolve conflicts for a specific PR
python3 .claude/skills/merge-resolver/scripts/resolve_pr_conflicts.py \
--pr-number 123 --branch-name "fix/my-feature" --target-branch "main"
# Dry-run mode (no side effects)
python3 .claude/skills/merge-resolver/scripts/resolve_pr_conflicts.py \
--pr-number 123 --branch-name "fix/test" --dry-run
Triggers
| Trigger Phrase | Operation |
|---|---|
resolve merge conflicts |
Auto-detect branch/PR and resolve |
fix conflicts on this branch |
Context-aware conflict resolution |
PR has conflicts with main |
Merge-based conflict resolution |
can't merge due to conflicts |
Analyze and fix blocking conflicts |
resolve PR conflicts |
Resolve conflicts for a specific PR number |
Process
Phase 0: Execution Capability Precondition (BLOCKING)
Run this self-check FIRST, before any context gathering, analysis, or plan. Conflict resolution requires shell execution: worktree creation, git merge, staging, commit, and git push. Without those tools you can only describe steps, never resolve anything.
| Step | Action | Verification |
|---|---|---|
| 0.1 | Confirm shell/Bash is available (git, worktree creation, git push) |
A tool result in this run shows a shell command executed |
| 0.2 | If shell is unavailable: return immediately with status [BLOCKED], one-line reason, route execution back to the orchestrator, and STOP | No resolution plan, phase list, or report is produced |
If shell execution is unavailable, do NOT produce a step-by-step resolution plan. A plan reads as completed work and is the exact failure this precondition prevents (issue #2646). Return BLOCKED and route execution back to the orchestrator.
Completion rule (applies to every execution phase below): mark a phase complete ONLY when a tool result in this run proves it ran. A plan is not a completion. Never report "create worktree", "merge", "push", or "run gates" as complete from instructions alone.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago Changed · -1 lines efb9dd88f88e
- 1mo ago Changed · +6 lines 3df45c5e243b
- 1mo ago Changed · +1 lines 3f5809144ad2
- 1mo ago Changed · +2 lines 97505cbd3c23
- 1mo ago Changed f8c67b0b2dbc
- 1mo ago First seen · 321 lines · 93 tokens per session scan A 88f9d20e41d1
merge-resolver is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 4,084 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
review-remote
Review open PR/MR and publish findings.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
ci-cd-pipeline-authoring
Use when a repository needs CI/CD - author GitHub Actions workflows so TaskTrooper's pipeline auto-detects your validate/build/test jobs and stage/preprod/prod deploys, and so a dispatch delivery profile can dispatch the production deploy.
ase-repo-review
Perform a holistic, human-reviewer-style critique of the currently staged Git changes (or, with --unstaged, of the unstaged and untracked changes, with --branch, of a branch against its base, or, with --commit, of a single commit) and emit an approve/reject verdict with prioritized, severity-tagged, line-cited…