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/agentic-swe/agentic-swe/conflict-resolvergit clone --depth 1 https://github.com/agentic-swe/agentic-sweWhat 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 | $0.00020 | $0.00744 |
| Opus 5 | $0.00010 | $0.00372 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
conflict-resolver 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/conflict-resolver
Detect, classify, and resolve git merge/rebase conflicts with structured reporting.
Prompt
You are resolving git conflicts. Detect conflicts, classify their complexity, attempt safe resolution, and report results.
Arguments: $ARGUMENTS
- If arguments specify a merge or rebase command, execute it and handle resulting conflicts.
- If no arguments, inspect the current worktree for existing unresolved conflicts.
Procedure
-
Detect conflict state:
- Check
git statusfor unmerged paths. - If no conflicts exist and no merge/rebase argument was given, report "no conflicts detected" and exit.
- If a merge/rebase command was requested, execute it and capture the result.
- Check
-
Inventory conflicting files:
- List each conflicting file path.
- For each file, extract the conflict markers (
<<<<<<<,=======,>>>>>>>). - Count conflict regions per file.
-
Classify each conflict:
- Trivial: One side added, other didn't touch (auto-resolvable by accepting the addition).
- Formatting: Only whitespace, import ordering, or line ending differences.
- Content: Both sides modified the same lines with different intent.
- Structural: File renamed/moved on one side, modified on other. Or deleted on one side, modified on other.
- Complex: Overlapping logic changes requiring human judgment.
-
Attempt resolution (safe cases only):
- Trivial: Accept the addition. Stage the file.
- Formatting: Accept the version consistent with the project's formatter config. Stage the file.
- Content (when one side is clearly a superset): Accept the superset. Stage the file.
- Structural/Complex: Do NOT auto-resolve. Report as requiring human review.
-
Verify resolution:
- For each resolved file, confirm no conflict markers remain.
- If all conflicts resolved, do NOT finalize the merge/rebase (do not commit or continue). Leave staged for human verification.
- Report what was resolved and what remains.
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 · 82 lines · 20 tokens per session scan A de22f402c217
conflict-resolver is a command published in the GitHub repository agentic-swe/agentic-swe (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 744 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.