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 automagik-dev/genie --skill mergegit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/merge)<a href="https://agentmods.dev/skills/automagik-dev/genie/merge"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/merge/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/automagik-dev/genie/merge"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/merge.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 | $0.00032 | $0.00849 |
| Opus 5.5 | $0.00013 | $0.00340 |
| Sonnet 5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
merge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge
A conflict is two intents meeting, not two texts disagreeing. Resolve it by understanding what each side was for. Always resolve; abandoning the operation returns the same conflict to the next person with less context than you have now.
See the state
Establish what is actually in progress before touching a file:
git status
git log --oneline --left-right --boundary HEAD...MERGE_HEAD
mapfile -t conflicted < <(git diff --name-only --diff-filter=U)
printf '%s\n' "${conflicted[@]}"
Record that list while the paths are still conflicted: once the markers are gone the same query returns nothing, and this is the list you stage at the end.
A rebase and a merge present the sides in opposite orders, so confirm which operation you are in before reading any hunk. During a rebase the side labelled as yours is the upstream branch, and the side labelled as theirs is the commit being replayed.
Find the intent
For each conflicting file, find the primary source of both changes:
git log -p --follow -- <path>
Read the commit messages, and where a commit points at a pull request or an issue, read that too. The wish that owns the work is the strongest source available in this repository: the criteria and the execution strategy say what the change was for in the author's own words. Keep reading until you can state each side's intent in one sentence.
Resolve each hunk
- Preserve both intents where they compose. Most conflicts are two independent edits that a mechanical tool could not interleave.
- Where they genuinely cannot compose, keep the one matching the stated goal of this merge and note the trade-off in your report.
- Never resolve by taking one side wholesale. Choosing a side without reading the hunk discards the other intent silently, which is exactly the failure a conflict exists to prevent.
- Never invent behaviour neither side asked for. A conflict is not an opportunity to refactor.
- Delete every conflict marker, then read the merged region as though it arrived as a fresh diff. It has to make sense on its own.
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.
- yesterday Changed · +3 lines 23d667f2f7d3
- 6d ago First seen · 71 lines · 32 tokens per session scan A 7ab2db62063a
merge is a skill published in the GitHub repository automagik-dev/genie (342 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 849 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 2026-09-17.
Other skills, from other repositories
tilth
Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…
resolving-merge-conflicts
Use when git merge or rebase fails with conflicts, you see 'unmerged paths' or conflict markers (<<<<<<< =======), or need help resolving conflicted files. Triggers: 'merge conflict', 'fix the conflicts', 'conflicting changes', 'resolve conflicts', 'can't merge'.
rca
Root-cause analysis and pre-commit fix verification for a PR, branch, commit, or stack trace. Detects bugfix vs feature; for a bugfix finds the commit that introduced it (the suspect set, via git blame/log), its intent, the releases it shipped in, and whether a proposed fix is complete; for a feature maps the blast…
refactor
Safely restructure code in an isolated git worktree with test-preserved, incremental transformations.
canonical-worktree-path-normalization
Resolve repo-relative paths against the canonical checkout root so shared state stays stable across Git worktrees.
classified-skill-listing-debug-telemetry
Emit low-cost debug telemetry for skill-listing batches that records batch size, initial-vs-dynamic mode, and cumulative sent count without logging the payload body.