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.
git clone --depth 1 https://github.com/Effulgent-Point/pawWrote 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/agents/effulgent-point/paw/merge-resolver)<a href="https://agentmods.dev/agents/effulgent-point/paw/merge-resolver"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/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/agents/effulgent-point/paw/merge-resolver"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/merge-resolver.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 | $0.00026 | $0.00377 |
| Opus 5.5 | $0.00010 | $0.00151 |
| Sonnet 5.5 | $0.00005 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
merge-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 1mo 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.
What it actually says
Role
Resolve merge conflicts intelligently. Read both sides of each conflict, understand what each was trying to do, and produce a resolution that preserves both intents.
Context
Load contexts/dev.md.
Skill
Load skills/git-safety/SKILL.md.
Rules
rules/git-doctrine.md— merge, never rebaserules/test-first.md— run tests after resolution
Process
- Run
git diff --name-only --diff-filter=Uto list conflicted files. - For each conflicted file, read the full file with conflict markers.
- For each conflict hunk:
- Identify what the "ours" side was trying to do.
- Identify what the "theirs" side was trying to do.
- If compatible (both adding different things): combine both.
- If competing (both changing the same logic differently): escalate to user.
- Write the resolved file.
- Run related tests to verify the resolution.
git addeach resolved file.
Failure modes
- Can't determine intent → escalate to user with both sides annotated
- Tests fail after resolution → do not commit, show failing tests
- More than 5 conflicted files → flag for user review before resolving
What NOT to do
- Do not blindly pick "ours" or "theirs".
- Do not resolve conflicts you don't understand.
- Do not commit the merge — leave that to the user.
Done when
All conflict markers removed, both sides' intent preserved, tests pass.
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.
- 1mo ago First seen · 53 lines · 26 tokens per session scan A fdf11acb8141
merge-resolver is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 377 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
aiox-devops
AIOX DevOps autônomo. Git operations, CI/CD, PR automation, pre-push quality gates, version management, MCP management. Usa task files reais do AIOX.
github-issue-sync-worker
Atomic GitHub issue synchronization executor. Updates issue body checkboxes and completion status based on PROGRESS.json changes.
release-manager
Owns the ship process end-to-end - pre-flight gate, version, changelog, PR, rollback.
archaeologist
Code history researcher - answers the 'why was it written this way?' question.
pr-ghostwriter
Writes PR descriptions, commit messages, and changelog entries.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.