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 agentmods add skills/luqueee/kivgraph/merging-pull-requestsnpx skills add Luqueee/kivgraph --skill merging-pull-requestsgit clone --depth 1 https://github.com/Luqueee/kivgraphWrote 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/luqueee/kivgraph/merging-pull-requests)<a href="https://agentmods.dev/skills/luqueee/kivgraph/merging-pull-requests"><img src="https://agentmods.dev/badge/skills/luqueee/kivgraph/merging-pull-requests.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01711 |
| Opus 5 | $0.00019 | $0.00856 |
| Sonnet 5 | $0.00008 | $0.00342 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
merging-pull-requests 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merging a Kivgraph pull request
This skill performs the final, destructive PR operation. A request to merge a
specific PR authorizes both the merge and deletion of that PR's head branch.
Do not use this skill for requests to prepare a PR, check whether it is ready,
or enable auto-merge. The workflow below is self-contained and must not load
another skill's SKILL.md at runtime.
Preconditions
- Treat the PR as review-ready only when the intended changes are committed and pushed, relevant local gates have passed, required GitHub checks have completed successfully, CodeRabbit has reviewed the latest head, every actionable finding is addressed or explained, and GitHub reports no merge conflict or other known blocker. Stop if any condition is missing; do not merge around an unresolved finding.
- Resolve exactly one PR. Use the PR number or URL supplied by the user; if it is absent, use the current branch's PR only when there is exactly one. Stop if the target is ambiguous.
- Fetch live PR metadata from GitHub. Confirm that the PR is open, not a draft,
mergeable, and has a concrete
headRefOid,headRefName,headRepository.nameWithOwner, base branch, and repository. Never infer these values from a stale local checkout. - Check required status checks and review state. Wait for pending checks and CodeRabbit; stop on a failure, conflict, missing required check, or a review decision that still requests changes.
CodeRabbit final gate
The final gate is about the current head SHA, not merely whether CodeRabbit has reviewed the PR at some point.
- Before waiting, record the current head SHA and a snapshot of all existing
CodeRabbit reviews, inline comments, issue comments, and thread states. Keep
each artifact's ID, commit or timestamp fields, body digest, and resolution
state where available. Set
reviewCycleStartedAtimmediately after this snapshot. Identify the bot by its GitHub account/login returned by the API, not by a string in the comment body. The usual login iscoderabbitai[bot], but do not assume it. - Wait until the CodeRabbit check or review for that exact SHA has completed. A queued, in-progress, absent, or API-inaccessible review is a blocker.
- Fetch all three surfaces again:
- pull-request reviews;
- pull-request review comments, including replies and threads;
- issue comments on the PR, which cover comments outside the diff.
- Compare the second snapshot with the first and save the second as the
postReviewSnapshot. Any new CodeRabbit finding that requests a change blocks the merge, even if CI is green. A new clean summary is not a finding, but it must be reported. - Check existing findings as well. Every CodeRabbit comment concerning the
current head must be resolved, obsolete with an evidence-based explanation,
or already fixed. Do not treat an old comment as harmless just because it
was posted on an earlier SHA. Unresolved review threads or a
CHANGES_REQUESTEDreview block the merge. - Issue comments do not expose
commit_id. Treat an issue comment as part of the current review cycle when its ID is new afterreviewCycleStartedAt, or its body orupdated_atchanged after that checkpoint. Evaluate its body and ID even without a commit field. Pre-existing unchanged issue comments remain historical, but their unresolved actionable content still blocks the merge; missingcommit_idalone is not uncertainty. If identity, timing, or status cannot otherwise be established, stop and report the uncertainty instead of guessing. After any fix and push, restart this gate from the new head SHA.
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 First seen · 139 lines · 39 tokens per session scan A f2e18fb93924
merging-pull-requests is a skill published in the GitHub repository Luqueee/kivgraph (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,711 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 2026-09-04.
Other skills, from other repositories
codestory-grounding
Use when an agent should ground a local repository with CodeStory before making source claims, planning edits, choosing tests, reviewing changes, or using broad retrieval evidence through the CodeStory plugin MCP.
graft
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
code-graph
This skill should be used when understanding code structure, finding dependencies between functions/classes, tracing call graphs, or exploring code relationships. Trigger phrases include 'code graph', 'call graph', 'who calls', 'what calls', 'find dependencies', 'code structure', 'inheritance', 'find paths'.
code-knowledge-graph
Codebase'i knowledge graph olarak analiz et. Dependency, call graph, hotspot analizi.