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 onur-aslan/sdd --skill mergegit clone --depth 1 https://github.com/onur-aslan/sddWrote 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/onur-aslan/sdd/merge)<a href="https://agentmods.dev/skills/onur-aslan/sdd/merge"><img src="https://agentmods.dev/badge/skills/onur-aslan/sdd/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/onur-aslan/sdd/merge"><img src="https://agentmods.dev/badge/skills/onur-aslan/sdd/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 | $0.00071 | $0.00815 |
| Opus 5.5 | $0.00028 | $0.00326 |
| Sonnet 5.5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
merge
Merges the source branch from $ARGUMENTS with the target branch into a reviewable integration branch, reconciling conflicts on the way, and leaves the target branch itself untouched.
Input
- source (required): the branch merged in, e.g.
feature/login. - target (optional): the branch merged into; default is the current branch.
- language (optional,
--lang <language>): the language the session runs in — the plan table, the questions and the reports; default is the language the user writes in.
Flow
flowchart TD
A[Resolve source and target refs] --> B{Working tree clean?}
B -- no --> Z1[Stop: ask the user to commit or stash]
B -- yes --> C{Target has no commit<br/>the source lacks?}
C -- yes --> M[Merge the source into a new branch off the target]
C -- no --> D[Dry-run the merge,<br/>touching the working tree not at all]
D --> F[Review each conflict and the merged result]
F --> G{riskless?}
G -- yes --> H[Resolve directly]
G -- no --> I[Show options + a recommendation,<br/>wait for the user's choice]
H --> P[Print every decision as a table, ask approval]
I --> P
P --> J{Approved?}
J -- no --> Z2[Stop: nothing was merged]
J -- yes --> M
M -->|fails| Z3[Abort the merge, drop the branch, report]
M --> K[Report the branch and every resolution]
Rules
Setup — Both refs must resolve to branches and the working tree must be clean; otherwise report and stop.
Branch — All the merge work goes on merge/<source>-into-<target>, branched from the target; the target branch itself is never modified.
Classify — every conflict (base / ours / theirs), and the merged result as a whole:
- Riskless — resolve it yourself: the sides do not interact, or the change is mechanical.
- Risky — the user decides: the sides touch the same behavior or contract, or the merge leaves something broken or inconsistent. Unsure counts as risky.
Ask when it is the user's call — one per turn, never batched: base/ours/theirs, then 2-3 options with the one you recommend, then the user's choice. Never decide it for them.
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.
- 2d ago First seen · 57 lines · 71 tokens per session scan A 990d5d78e567
merge is a skill published in the GitHub repository onur-aslan/sdd (10 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 815 once invoked, about $0.0003 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 2026-11-12.
merge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mergeonur-aslan/sdd | Skill | 10 | yesterday | MIT | A | 71 | Claude Code |
| finishing-a-development-branchrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 44 | Claude Code, Codex |
| using-git-worktreesrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 36 | Claude Code, Codex |
| comet-archiverpamis/comet | Skill | 3.3k | yesterday | MIT | A | 35 | Claude Code, Codex |
| comet-archiverpamis/comet | Skill | 3.3k | yesterday | MIT | A | 34 | Codex |
| comet-github-issue-fixrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 71 | Claude Code, Codex |
| comet-github-pr-reviewrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 69 | Claude Code, Codex |