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/explainnpx skills add maxedapps/agent-skills --skill explaingit 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 | $0.00087 | $0.01459 |
| Opus 5 | $0.00044 | $0.00730 |
| Sonnet 5 | $0.00017 | $0.00292 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
explain 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual-only gate: If the user did not explicitly invoke
explainby name, stop without drafting Markdown/HTML or installing renderer dependencies. Explain that this skill is manual-only.
Explain
Critical rules
- Explain only. Do not implement, fix, or modify the subject; write only the requested Markdown/HTML artifacts and any required local dependency install.
- Lead with the answer or mental model, then supply only the context needed to support it.
- Ground claims in supplied/current code, data, artifacts, or conversation context. For code, cite paths and symbols and distinguish observed behavior from inference.
- Default to 3–6 sections, paragraphs of at most three sentences, at most one useful diagram, and 1–2 focused excerpts normally no longer than 15 lines each. Exceed a default when correctness requires it.
- Do not repeat the same information in prose, code, tables, and diagrams. Give each retained modality a distinct job.
- Redact secrets, credentials, tokens, PII, and irrelevant sensitive values from prose, excerpts, diagrams, and paths returned to the user.
- Before designing any explanation, read
references/explanation-design.md. It is mandatory.
Workflow
- Interpret the requested subject, audience, desired depth, output location, and title. Ask only about a consequential ambiguity; otherwise use a concise maintainer-oriented default.
- Inspect the supplied or current context before drafting. For code/systems/data, read the relevant files, callers, symbols, schemas, and tests; for a prior plan, review, or agent statement, inspect the available conversation and named artifacts without reconstructing missing context.
- Research only missing, current external claims with the
web-researchskill. If retrieval is unavailable, state the limitation and omit unsupported claims rather than guessing. - Before choosing the structure, read
references/explanation-design.md, then select the smallest archetype, evidence labels, trace, excerpts, and optional visual that answer the request. - Draft the answer-first explanation. Use code path/symbol citations, label material observations versus inferences, and include safeguards, trade-offs, or gaps only when they affect understanding.
- Write the Markdown to the user-selected location. If none was selected, use a fresh OS temporary directory; choose a fresh
.htmlpath there too. - Self-edit against the critical rules and the reference's deletion pass. Verify every claim against its cited context and remove duplicated modalities.
- Resolve the installed skill directory to an absolute path. If its dependencies are unavailable, run this idempotent lockfile-based setup once from that directory:
What ships with it
9 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 · 79 lines · 87 tokens per session scan A b6a71d8645b4
explain is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 18d ago), licensed MIT. It adds 87 tokens to every session and 1,459 once invoked, about $0.0004 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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…