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 aliengiraffe/vigilante --skill vigilante-conflict-resolutiongit clone --depth 1 https://github.com/aliengiraffe/vigilanteWrote 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/aliengiraffe/vigilante/vigilante-conflict-resolution)<a href="https://agentmods.dev/skills/aliengiraffe/vigilante/vigilante-conflict-resolution"><img src="https://agentmods.dev/badge/skills/aliengiraffe/vigilante/vigilante-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/aliengiraffe/vigilante/vigilante-conflict-resolution"><img src="https://agentmods.dev/badge/skills/aliengiraffe/vigilante/vigilante-conflict-resolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00556 |
| Opus 5 | $0.00017 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
vigilante-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 12d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vigilante Conflict Resolution
Overview
Use this skill after Vigilante has already opened a pull request and a follow-up rebase onto origin/main hits conflicts. Work only inside the assigned worktree, resolve the conflicts with the smallest safe change, rerun validation, push the updated branch, and keep the linked GitHub issue informed.
Workflow
- Inspect the current rebase state in the assigned worktree and start the rebase onto the provided base branch if it has not already begun.
- Read repository instructions that affect the touched files before editing.
- Comment on the issue when conflict resolution begins and again for meaningful milestones or failures.
- Resolve only the conflicts needed to complete the rebase cleanly, commit by commit, while preserving the original issue specification and branch intent.
- Use
vigilante commitfor all commit-producing operations. Do not usegit commitor GitHub CLI commit flows directly. - Preserve the user's existing git author, committer, and signing configuration for every rebase rewrite, amend, or conflict-resolution commit, and do not overwrite
git configwith a coding-agent identity. - Do not add
Co-authored by:trailers or any other agent attribution for Codex, Claude, Gemini, or similar coding-agent identities. - If the rebase fails, post-rebase validation fails, or the current session state is unclear, inspect
vigilante logs --repo <owner/name> --issue <n>before retrying so the persisted session transcript becomes the factual source for the next safe action. - After inspecting the log, either continue with the smallest safe fix, rerun the requested validation, or report a blocker on the issue when the transcript shows the branch should not be retried automatically.
- Push the updated branch back to GitHub after the rebase and requested validation succeed.
- Report the final result clearly on the issue, including any remaining blocker if the conflicts cannot be resolved safely.
Guardrails
- Stay inside the provided worktree.
- Do not broaden the change beyond the conflicting files unless required to restore build or test health.
- Keep the original issue behavior authoritative; do not drop commits or rewrite away issue scope just to remove conflicts.
- Do not rewrite commit authorship, committer identity, signing configuration, or commit trailers to attribute the branch history to the coding agent.
- Do not claim the branch is merge-ready unless the requested validation actually passed.
- Report blockers immediately with
vigilante gh issue comment.
What ships with it
1 file 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.
- 12d ago First seen · 31 lines · 35 tokens per session scan A 2187000521a6
vigilante-conflict-resolution is a skill published in the GitHub repository aliengiraffe/vigilante (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 556 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pipeline-conductor
Use when a pipeline conductor session is being seeded, or when inspecting/debugging one. Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, preflight every candidate to one deterministic claim verdict, stand up one worker…
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
prepare-pr
LOAD THIS WHENEVER A TASK WILL OPEN OR UPDATE A PR — including a PR you raise incidentally while doing something else — and run the full loop without waiting to be asked. End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS…
kirocrew-worktree-dev
HARD RULE for developing the Kiro Crew source repo ITSELF (not for users' own projects): every change is built and verified inside a git worktree, never against the live gateway. Covers worktree creation, the blocking local build gates (pytest + isort + flake8 + mypy + tsc + vitest), the built-dist gotcha, feature…
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.