semantic-merge

semantic-merge is a skill for Claude Code, Codex from postindustria-tech/agentic-toolkit. It costs 153 tokens per session (2,411 once invoked), scanned A, original, MIT.

A branch-integration method that resolves conflicts by checking whether the combined code still behaves correctly. A branch is a separate line of development in Git.

In plain words
What is it for?
Use it to merge branches, resolve conflicts per file, keep generated data and lockfiles from being hand-merged, and verify the result with integration, behavior, or end-to-end tests.
Why use it?
A merge can complete without text conflicts while still combining related changes incorrectly.

Skill for Claude CodeCodex

Part of the dev-practices plugin — 9 skills, 9 agents shipped together

Install

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.

agentmods
npx agentmods add skills/postindustria-tech/agentic-toolkit/semantic-merge
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill semantic-merge
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Or install dev-practices, the plugin that ships this one along with the rest of its 9 skills, 9 agents.

Wrote 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.

agentmods badge for semantic-merge

README.md
[![agentmods](https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/semantic-merge.svg)](https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/semantic-merge)
Your own site
<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/semantic-merge"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/semantic-merge.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.02411
Opus 5 $0.00077 $0.01205
Sonnet 5 $0.00031 $0.00482
Haiku 4.5 $0.00015 $0.00241

Measured 5d ago against content hash e3c42ca58fdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

semantic-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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/merge-survey.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dev-practices/skills/semantic-merge/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Merge

Merge branches so the RESULT is correct, not merely conflict-free.

Governing principle: a textual auto-merge is not a correct merge. Git resolves by lines; it silently mis-merges logic where both sides changed related code, and it "cleanly" auto-merges files that are semantically broken. Every merge is verified at the behavior layer, not the "no conflict markers" layer.

Hard rules (non-negotiable)

  • Never content-merge generated or tool-owned data files. Lockfiles (*.lock), dependency snapshots, generated code/stubs, database snapshots, task-tracker data (issue journals/DBs), migration-hint markers, and coverage/ duplication baselines are NOT source. Pin them to ONE side (usually the target base) or regenerate them after the merge — never hand-splice their contents. For any data store shared across worktrees, a content merge causes real data loss: stop and ask if it is more than a trivial marker.
  • "Unit tests pass" is not "merge is correct." The gate is import-all collection plus the behavior-level suite (integration / BDD / e2e). A merge can be unit-green and still broken across files.
  • A clean auto-merge still needs review. Conflicts are the loud failures; mis-merges are the silent ones. Phase 6 exists for exactly this.
  • Isolate the work. Never do a large/divergent merge in a dirty working tree — use a throwaway worktree so uncommitted changes and shared data stores are safe.

Phase 1 — Map the DAG (before touching anything)

Do not merge blind. Establish the shape with scripts/merge-survey.sh <A> <B> [--onto <base>], or by hand:

git merge-base --is-ancestor A B      # is one branch already contained in the other?
BASE=$(git merge-base A B)
git rev-list --count $BASE..A         # commits unique to A
git rev-list --count $BASE..B         # commits unique to B
git rev-list --count A..<base>        # how far behind the integration base
  • Linear (one contains the other) → the merge is trivial; just fast-forward / merge the superset.
  • Divergent → the real work is only where the unique commits of each side overlap. The huge "files touched by both" number is mostly shared base history — ignore it.

Read the full file on GitHub · 202 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 202 lines · 153 tokens per session scan A e3c42ca58fdb

Subscribe to this mod's changes

semantic-merge is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 153 tokens to every session and 2,411 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens