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/maxedapps/agent-skills/create-changes-reportnpx skills add maxedapps/agent-skills --skill create-changes-reportgit clone --depth 1 https://github.com/maxedapps/agent-skillsWhat 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 | $0.00103 | $0.01987 |
| Opus 5 | $0.00051 | $0.00993 |
| Sonnet 5 | $0.00021 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
create-changes-report 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an interactive changes report
This skill is a completion gate for repository changes. Before the final response for any task that changed code, tests, configuration, schemas, or infrastructure, produce ONE self-contained HTML file (no CDN, works from disk). A reviewer must understand and assess the changes in ~5 minutes without first reading the source; every key number and claim is one click from evidence.
Save it under reports/ as a descriptive kebab-case *-changes.html. Make that path the primary review handoff; keep the chat summary brief.
This artifact does not replace code-review or an owning workflow's finding authority. If report preparation uncovers a new material defect, stop, return it to the owning workflow for disposition and verification, then regenerate from the resolved state.
Start from assets/report-template.html — visual system, highlighter, popover/jump JS, and one working example of every component. Copy it and replace content; do not restyle from scratch.
A candidate is the creator-QA-complete exact bytes. Any edit creates a new candidate. An owning workflow may require a fresh reviewer to read references/artifact-review.md (reviewer-only honesty/completeness/usefulness/precision contract; read when independently reviewing a candidate). Keep the review outcome outside the HTML.
The altitude rule
- The main page is a 5-minute read: what was built, how it fits, what's risky, what to decide. No exhaustive lists on it.
- Depth lives behind clicks: inventories, per-file breakdowns, and protocol details go in popovers.
- Every stat tile and load-bearing claim is clickable (
data-popordata-goto). - At most five
pre.hlsnippets across Critical points plus optional Additional key code. One source of truth per excerpt; never duplicate.
Workflow
1 · Gather evidence (before writing any HTML)
- Establish exact scope from
git status, staged/unstaged diffs, and any baseline or commits. Include new/untracked files; never infer changes from memory. - Read the changed source and tests, plus the plan/spec, tracker, and prior review notes when they exist.
- Run the project's required check suite yourself and record exact commands and real results. Never report checks or numbers you did not reproduce.
- Extract popover data: changed-file inventory and line deltas; test names via
grep -hoE '(it|it\.effect|describe)\(\s*"[^"]+"' <test files>; per-file sizes (wc -l); applicable counts (endpoints, tables, packages, migrations, versions). - Trace the main behavior from entry to side effects; note compatibility, data, auth, error, and rollback implications.
- For critical or broad changes, run independent review passes over major surfaces and keep only calibrated findings.
What ships with it
3 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.
- 2d ago First seen · 109 lines · 103 tokens per session scan A 801d203bba56
create-changes-report is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 1,987 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…