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/shdennlin/agent-plugins/explainnpx skills add shdennlin/agent-plugins --skill explaingit clone --depth 1 https://github.com/shdennlin/agent-pluginsWhat 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 | $0.00119 | $0.00594 |
| Opus 5 | $0.00060 | $0.00297 |
| Sonnet 5 | $0.00024 | $0.00119 |
| Haiku 4.5 | $0.00012 | $0.00059 |
Grade A, and why
digest: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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain
Turn unfamiliar code or a finished investigation into a visual explainer. digest covers delta (what changed); explain covers state (what is this, how does it work, why is it like this, where's the bug from).
Usage
$explain # explain the current conversation's findings
$explain src/auth/ # how this module works
$explain handleRetry # this function's role in the flow
$explain "why saga pattern here?" # design rationale via git archaeology
$explain src/ -f "new teammate" # onboarding tour
Options
| Flag | Description |
|---|---|
-f, --for <audience> |
Tailor for an audience — free-form string (manager, non-technical, "new teammate", ...). Default: developer |
Output is always a self-contained HTML explainer written to the project root (explain-<slug>-<YYYY-MM-DD>.html), plus a one-paragraph conclusion in the terminal.
Process
- No arguments → conversation mode (inline, no dispatch): the findings live in the current conversation, so build the explainer directly — read the visual spec at
../../templates/html-explainer.md(relative to this directory), assemble sections from the section library, write the file. If the conversation holds no investigation yet, say so in one line and stop. - Arguments → investigation mode (dispatch): classify the target (existing path → file/module; identifier-like → symbol; else → question) and dispatch the explain agent.
Agent Dispatch (investigation mode only)
Use the companion explain-agent.md in this directory as the agent prompt. Provide it with:
- Target and target kind (file/module | symbol | question)
- Audience (free-form string, default
developer) - Output slug (path → basename; symbol → kebab; question → first ~5 significant words, kebab)
- The HTML template at
../../templates/html-explainer.mdrelative to this directory
The agent uses $PROJECT_ROOT (set by the init hook) or falls back to git rev-parse --show-toplevel.
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.
- yesterday First seen · 42 lines · 119 tokens per session scan A 600ddf4637c1
digest:explain is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 119 tokens to every session and 594 once invoked, about $0.0006 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.