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 zgsm-ai/costrict --skill roo-conflict-resolutiongit clone --depth 1 https://github.com/zgsm-ai/costrictWrote 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/zgsm-ai/costrict/roo-conflict-resolution)<a href="https://agentmods.dev/skills/zgsm-ai/costrict/roo-conflict-resolution"><img src="https://agentmods.dev/badge/skills/zgsm-ai/costrict/roo-conflict-resolution/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/zgsm-ai/costrict/roo-conflict-resolution"><img src="https://agentmods.dev/badge/skills/zgsm-ai/costrict/roo-conflict-resolution.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.01814 |
| Opus 5 | $0.00028 | $0.00907 |
| Sonnet 5 | $0.00011 | $0.00363 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
roo-conflict-resolution 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 11d 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.
This is a copy
98% identical to roo-conflict-resolution — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoStrict Conflict Resolution Skill
When to Use This Skill
Use this skill when the task involves:
- Resolving merge conflicts for a specific pull request
- Rebasing a branch that has conflicts with the target branch
- Understanding and analyzing conflicting code changes
- Making intelligent decisions about which changes to keep, merge, or discard
- Using git history to inform conflict resolution decisions
When NOT to Use This Skill
Do NOT use this skill when:
- There are no merge conflicts to resolve
- The task is about general code review without conflicts
- You're working on fresh code without any merge scenarios
Workflow Overview
This skill resolves merge conflicts by analyzing git history, commit messages, and code changes to make intelligent resolution decisions. Given a PR number (e.g., "#123"), it handles the entire conflict resolution process.
Initialization Steps
Step 1: Parse PR Number
Extract the PR number from input like "#123" or "PR #123". Validate that a PR number was provided.
Step 2: Fetch PR Information
gh pr view [PR_NUMBER] --json title,body,headRefName,baseRefName
Get PR title and description to understand the intent and identify the source and target branches.
Step 3: Checkout PR Branch and Prepare for Rebase
gh pr checkout [PR_NUMBER] --force
git fetch origin main
GIT_EDITOR=true git rebase origin/main
- Force checkout the PR branch to ensure clean state
- Fetch the latest main branch
- Attempt to rebase onto main to reveal conflicts
- Use
GIT_EDITOR=trueto ensure non-interactive rebase
Step 4: Check for Merge Conflicts
git status --porcelain
git diff --name-only --diff-filter=U
Identify files with merge conflicts (marked with 'UU') and create a list of files that need resolution.
Main Workflow Phases
Phase 1: Conflict Analysis
Analyze each conflicted file to understand the changes:
- Read the conflicted file to identify conflict markers
- Extract the conflicting sections between
<<<<<<<and>>>>>>> - Run git blame on both sides of the conflict
- Fetch commit messages and diffs for relevant commits
- Analyze the intent behind each change
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.
- 11d ago First seen · 257 lines · 56 tokens per session scan A 4f7ab7c6e781
roo-conflict-resolution is a skill published in the GitHub repository zgsm-ai/costrict (4,408 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,814 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to roo-conflict-resolution, differing in 34 lines, and is treated as a copy.
Other skills, from other repositories
git-workflow
Use this skill when working with git — making commits, creating branches, resolving merge conflicts, opening pull requests, or reviewing diffs. Apply whenever the user asks about version control operations.
issue-triage
Triage GitHub issues through the canonical state machine — classify, label, deduplicate, request missing info, write agent briefs, and manage stale issues. Use on demand or on a triage cron.
lastlight-client
Install the lastlight CLI and connect it as a CLIENT to an existing Last Light server — log in, save the token, and verify the connection. Use when the user wants to "connect / point my lastlight CLI at a server", "log in to Last Light", "set up the lastlight client", or run lastlight commands against a remote…
repo-health
Generate a health report for a GitHub repository — open-issue and PR backlog, unreviewed PRs, stale needs-info, failing CI, and the resulting action items. Use for a status report or on a weekly cron.
resolve-fixed-pr-comments
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
review-local-changes
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.