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/legendapp/legend-skills/git-integratenpx skills add LegendApp/legend-skills --skill git-integrategit clone --depth 1 https://github.com/LegendApp/legend-skillsWrote 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/legendapp/legend-skills/git-integrate)<a href="https://agentmods.dev/skills/legendapp/legend-skills/git-integrate"><img src="https://agentmods.dev/badge/skills/legendapp/legend-skills/git-integrate.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 5.1 | $0.00101 | $0.01764 |
| Opus 5 | $0.00051 | $0.00882 |
| Sonnet 5 | $0.00020 | $0.00353 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
git-integrate 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Integrate
Own a rebase, merge, cherry-pick, or revert through verified completion. If one is already in progress, take it over and continue or repair it before considering new work. Otherwise, safely start the operation explicitly requested by the user. This is not a general Git command runner: do not choose an integration strategy or perform unrelated commit, branch, stash, reset, remote, or worktree maintenance.
Hard stop: For new work, proceed only when the requested operation and history shape are 100% clear. For an in-progress operation, continue it without requiring the user to restate its method or target when Git state makes the operation and next action clear. Resolve a conflict only when its intended result is also clear from repository evidence. Otherwise stop before mutating Git or files and ask the user with concrete options. Never choose a default; an incorrect history operation or resolution is worse than an interruption.
Workflow
-
Inspect state. Run full
git status,git status --short --branch, andscripts/inspect-operation.shwhen available. Record the current branch andHEAD. Resolverebase-merge,rebase-apply,MERGE_HEAD,CHERRY_PICK_HEAD,REVERT_HEAD, and the sequencer directory withgit rev-parse --git-path.Active Git state determines the operation to continue; do not start another or ask the user to choose a new method or target. It does not by itself establish the intended combined behavior or prove that
--continueis the correct immediate action. -
Continue an active operation. Read
git status, the operation metadata and todo state, the current operation commit, unmerged index stages, staged changes, and working-tree changes. Determine whether the operation is ready to continue or stopped for a conflict, an edit instruction, a failed exec, an empty commit, a pending commit, or another reason.Route conflicts through the resolution workflow below. For an edit or failed exec, verify the requested edit or command result before continuing. For an empty commit, require explicit approval before keeping, dropping, or skipping it. If the stop reason or next action is unclear, preserve the exact state and ask; never blindly continue an operation merely because it is active.
What ships with it
2 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.
- 6d ago First seen · 64 lines · 101 tokens per session scan A 974ff3225a78
git-integrate is a skill published in the GitHub repository LegendApp/legend-skills (37 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,764 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…