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 event4u-app/agent-config --skill merge-conflictsgit clone --depth 1 https://github.com/event4u-app/agent-configWrote 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/event4u-app/agent-config/merge-conflicts)<a href="https://agentmods.dev/skills/event4u-app/agent-config/merge-conflicts"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/merge-conflicts/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/event4u-app/agent-config/merge-conflicts"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/merge-conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 154 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 255 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00029 | $0.02444 |
| Opus 5 | $0.00015 | $0.01222 |
| Sonnet 5 | $0.00006 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
merge-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 8d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
merge-conflicts
When to use
Use this skill when:
- A merge or rebase produces conflicts
- The user asks to "resolve conflicts", "fix merge", or "update branch"
- CI fails because the branch is behind main
- The
prepare-for-reviewcommand encounters conflicts
Procedure: Resolve merge conflicts
0. Classify before resolving — and never start in the GitHub web editor
A CONFLICTING PR is not a signal to open the web editor. The web editor
cannot tell generated from authored, so it presents a mechanical regeneration
and a real human decision as the same three-way merge — which is how a generated
file gets hand-merged into a state matching neither branch.
So classify locally first, before resolving anything. Sort every conflicted path into three classes, because the correct resolution differs per class and only one of them is a judgement call:
| Class | What it is | Resolution |
|---|---|---|
| generated | a build output, an index, a compiled manifest — anything a generator writes from a source in the tree | re-run the generator. Never mix hunks, and note that a clean auto-merge of a generated file is still wrong: it can produce a file matching neither branch |
| remeasured | a baseline, budget, or ratchet number a CI gate compares against | re-run the measurement on the merged tree and record what it says. Two branches legitimately measured two different trees, so there is no side to take — and picking one is how a ratchet silently loosens |
| authored | prose, source, config a human wrote | a human decision — read both sides. This is what the rest of this skill is about |
Getting the class wrong is the expensive direction: hand-merging a generated file, or picking a side on a measured one, both produce a plausible-looking file that no branch ever had. If the project ships a tool that does this classification, run it before touching the conflict; where it does not, the three-way sort above is still the first step.
This is a checklist item, not a gate — nothing enforces it (road-to-merge-hotspot-drawdown 4.3).
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.
- 8d ago First seen · 256 lines · 29 tokens per session scan A 730d6d9828a5
merge-conflicts is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,444 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 2026-09-04.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
odh-llm-d-release
Orchestrate the opendatahub-io release for all llm-d components in one cycle. Collects upstream(llm-d) versions, auto-discovers the release tracker issue, then spawns parallel sub-agents — one per component (release branch, Konflux onboarder workflow, PR validation, approve+merge, Quay image verify, GitHub draft…
pr-jira-linker
Find and link Jira issues to PRs/MRs that are missing Jira references. Supports single PR/MR linking and batch audit of configured repos. Use when the user mentions "link PR to Jira", "scan PRs", "PR audit", "MR missing Jira", "link merge request", or wants to connect code changes to Jira for traceability.
gist-upload
Use this skill to upload a summary or plan from the current conversation as a GitHub Gist using the gh CLI.
appstore-archive-uploader
App Store IPA/PKG archives: set version/build numbers, archive, export, upload, or publish with asc xcode before TestFlight/App Store submission.
vllm-backport-push-report
Push a triage report to GitHub under a timestamped directory in reports/. Use after the agent writes the report markdown and has ranked.json ready. Outputs the report URL to stdout.