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/ivklgn/ai-kit/explain-branch-changesnpx skills add ivklgn/ai-kit --skill explain-branch-changesgit clone --depth 1 https://github.com/ivklgn/ai-kitWrote 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/ivklgn/ai-kit/explain-branch-changes)<a href="https://agentmods.dev/skills/ivklgn/ai-kit/explain-branch-changes"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/explain-branch-changes.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 | $0.00162 | $0.01598 |
| Opus 5 | $0.00081 | $0.00799 |
| Sonnet 5 | $0.00032 | $0.00320 |
| Haiku 4.5 | $0.00016 | $0.00160 |
Grade A, and why
explain-branch-changes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Branch Changes
Turn the current branch's changes into a briefing a person who has never seen code can read. The reader may be a product manager, designer, support agent, marketer, or executive. They care about what changes for users and the business — never about how the code does it.
Write the briefing in the language the user communicates in. If the user writes in Russian, the briefing is in Russian.
The process:
- Collect the branch changes (git)
- Mine the changes and project docs for product meaning
- Translate to human language and deliver the briefing
Step 1: Collect the Changes
Detect the base branch and gather the raw material:
BASE=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@')
if [ -z "$BASE" ]; then
BASE=$(git rev-parse --verify main >/dev/null 2>&1 && echo main || echo master)
fi
git log $BASE..HEAD --pretty=format:"%h %s%n%b"
git diff $BASE...HEAD --stat
git diff $BASE...HEAD
Include uncommitted work (git status --short, git diff HEAD) if present — the reader wants the state of the branch, not just its commits.
Handle the edge cases in the reader's terms, not git's:
- Not a git repository → say this folder has no change history to read, and stop.
- On the base branch / no changes → say there is no work-in-progress here; offer to describe what shipped recently (last ~10 commits on the base branch) instead.
- Huge diff (thousands of lines) → work from
--stat, commit messages, and targeted reads of the most-changed and most user-facing files. Never skip Step 2 because the diff is big.
Step 2: Mine for Product Meaning
The diff says what changed; the surrounding context says why. Gather both:
- Commit messages and branch name — often contain the intent and ticket IDs.
- PR description —
gh pr viewif a PR exists (ignore errors if not). - User-visible strings in the diff — UI labels, button texts, error messages, emails, notification texts, translation files. These are the single best source for a product summary: they show exactly what a user will see.
- Docs touched or nearby — README, CHANGELOG, docs/, design docs,
.archcore/or similar knowledge bases. If the project documents the changed area, read it to name features the way the project names them. - Tell-tale files — migrations (data storage changed), feature flags (built but switched off), config/infra files, dependency manifests, test-only changes. See references/change-types.md for how to recognize and phrase each type.
- The code itself — read enough of the changed code to understand the actual behavior change. Use it for understanding only; none of it surfaces in the output.
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.
- 4d ago First seen · 107 lines · 162 tokens per session scan A 37e16a7b29cc
explain-branch-changes is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 1,598 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 2026-08-30.
Other skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
alipay-webhooks
Receive and verify Alipay (Antom / Alipay+) webhook notifications. Use when setting up Alipay webhook handlers, debugging RSA256 Signature header verification, or handling payment events like notifyPayment, notifyCapture, notifyRefund, notifyAuthorization, and notifyDispute.