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 commands/sigistry/marketplace/resolve-conflictsgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/resolve-conflicts)<a href="https://agentmods.dev/commands/sigistry/marketplace/resolve-conflicts"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/resolve-conflicts.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 5.1 | $0.00016 | $0.00778 |
| Opus 5 | $0.00008 | $0.00389 |
| Sonnet 5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
resolve-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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk through an in-progress merge or rebase conflict file by file, reconstruct what each side intended, and propose a resolution that preserves BOTH intents rather than blindly taking one side. With approval, apply the resolution via Edit. Use this whenever git status shows "Unmerged paths."
Process
Step 1: Confirm a conflict is in progress
Run git status. Confirm the repo is mid-merge (MERGING) or mid-rebase (REBASE), and collect the "Unmerged paths" list. If there is no conflict in progress, say so and stop. Identify which ref is OURS and which is THEIRS:
- Merge: OURS = current branch (
HEAD), THEIRS = the branch being merged (MERGE_HEAD). - Rebase: OURS = the commit being replayed onto (
HEAD), THEIRS = your commit being replayed (REBASE_HEAD). Note this inversion for the user, during rebase "ours" and "theirs" feel backwards.
Step 2: Understand the shared history
git merge-base HEAD MERGE_HEAD(or the rebase equivalent), the common ancestor (BASE).- List conflicted files. If there are multiple conflicted files, dispatch the conflict-resolver agent to handle them and synthesize per-file resolutions; otherwise proceed inline.
Step 3: For each conflicted file, reconstruct intent
Read the file's conflict markers (<<<<<<< ======= >>>>>>>). For each hunk:
- Extract BASE via
git show :1:<path>, OURS via:2:<path>, THEIRS via:3:<path>. - Run
git log --oneline -5 <ourref> -- <path>andgit log --oneline -5 <theirref> -- <path>to see what each side was doing. - Use
git blameon the surrounding lines of each side to learn WHY each change was made.
State plainly: what OURS changed vs BASE, what THEIRS changed vs BASE, and whether they overlap logically or merely textually.
Step 4: Propose a semantic merge
- Non-overlapping intents (both added distinct things): keep both.
- Overlapping logic (both edited the same behavior): reconcile into one version that satisfies both goals, do not silently drop either side's fix.
- True contradiction: surface it, explain the trade-off, and ask the user to choose. Never guess on a genuine semantic conflict.
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.
- 2d ago First seen · 48 lines · 16 tokens per session scan A f1b694733749
resolve-conflicts is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 778 once invoked, about $0.0001 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 commands, from other repositories
build
Guided feature development with approval gates at each phase.
adv-codex
Send a prompt to Codex CLI and return the response.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
make
Create structured implementation plan in docs/plans/.
review
Pressure-test an important decision, plan, proposal, strategy, architecture, or recommendation with adaptive depth and token-efficient verification.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.