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 kBashar/myagentskills --skill merge-conflictsgit clone --depth 1 https://github.com/kBashar/myagentskillsWrote 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/kbashar/myagentskills/merge-conflicts)<a href="https://agentmods.dev/skills/kbashar/myagentskills/merge-conflicts"><img src="https://agentmods.dev/badge/skills/kbashar/myagentskills/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/kbashar/myagentskills/merge-conflicts"><img src="https://agentmods.dev/badge/skills/kbashar/myagentskills/merge-conflicts.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 | $0.00050 | $0.01706 |
| Opus 5.5 | $0.00020 | $0.00682 |
| Sonnet 5.5 | $0.00010 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00171 |
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 23d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
merge-conflicts
Overview
Report every conflict a merge of two branches would produce, where each side came from, and what each resolution does — as a page in the browser plus a short overview in the chat. Analysis only: the repository must be byte-for-byte unchanged afterwards — same files, index, branches, and HEAD. The one file the skill writes is the report page, which render.sh puts in ${TMPDIR:-/tmp}/merge-conflicts/, outside the repository.
Inputs
Two branches. <first> receives the merge, <second> merges into it ("merge feature/login into main" → first = main, second = feature/login). Remote refs such as origin/main work as given. If only one branch is named, <first> is the current branch (git branch --show-current) — say so in the report. If the direction is unclear, ask.
Read-only rule
Use only these git subcommands: merge-tree, merge-base, log, show, blame, diff, grep, rev-parse, cat-file, branch --show-current. Use Read/Grep/Glob freely. Run the two bundled scripts with bash.
If you need information that only another command gives (fetch, checkout, merge, stash, …), stop and ask the user, naming the command and why. Analyze the local refs as they are; the report header shows which commits you analyzed.
Workflow
-
Collect the facts. Run the script from the target repo (
scripts/is in this skill's directory). Passrepo-dironly when the repo is elsewhere, as an absolute path:bash scripts/conflicts.sh <first> <second> [repo-dir]Exit 2 = bad input (message says which); exit 3 = git older than 2.38. Show the message and stop.
CONFLICTED_FILES=0= clean merge; report that and stop.Each conflict starts with
--- CONFLICT <n>:;<n>numbers the conflicts across the whole report. Per conflicted file the output givesTYPEand theCOMMITSon each side since the merge base; per conflict, the diff3 text (sections labelled with the branch names) plus aBLAMEof each side's lines.^<sha>in a blame line = unchanged since the merge base, not part of that side's change.
What ships with it
3 files 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.
- 23d ago First seen · 90 lines · 50 tokens per session scan A 38e50ba50b7c
merge-conflicts is a skill published in the GitHub repository kBashar/myagentskills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,706 once invoked, about $0.0002 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 2026-10-07.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.