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/a1f/agent-templates/explainnpx skills add a1f/agent-templates --skill explaingit clone --depth 1 https://github.com/a1f/agent-templatesWhat 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 | $0.00048 | $0.01334 |
| Opus 5 | $0.00024 | $0.00667 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00133 |
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 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain
Explain a slice or a PR in plain words — for someone who has never seen the code.
Do it the way Thing Explainer does — hard things in common words, so a pencil becomes a "writing stick." Show the impact, not the mechanics.
/explain <id> [--issue=N]
<id> = a slice (4, 7), a PR row (4.2, 5.1), or a GitHub PR (#92)
1. Find the slice or PR (don't guess; ask if unsure)
2. Read just enough (the row + the "why", never the whole diff)
3. Write it plain (2–3 short paragraphs)
Phase 1 — Find the slice or PR
Resolve <id> in this order:
- Empty → ask which slice or PR they mean (or offer the current branch's PR,
gh pr view --json title,body). #92orPR 92→ a GitHub PR.gh pr view 92 --json title,body,files; take the "why" from its body (no such PR → ask). Go to Phase 3.- A bare or dotted number → open the plan issue (
gh issue view <N> --json body). Match the id whole against both tables. The table it sits in decides: PR breakdown → PR row, slice table → slice (including a hand-inserted4.5). Whole-cell, so4.2≠14.2. - No single match → a whole number may be a GitHub PR; confirm "Did you mean PR
#?" before
gh pr view <id> --json title,body. If it errors, the id is dotted, or both tables match, ask which they mean. - Anything else (a word, a slug) → ask which slice or PR they mean.
Find the plan issue: --issue=N if given, else gh issue list --state all --label Plan,
then gh issue list --state all --search "Build plan in:body". One match, use it;
many, narrow then ask; zero, ask — show the issue # and title.
Phase 2 — Read just enough
Pull the facts, not the whole diff:
- Slice or PR row → its row, and the issue's
## The problem/## What we're buildingfor the "why". For a slice, also the PRs under it; for a PR row, its parent slice. - A PR row often links its merged PR (a
#number); else find it unmistakably (gh pr list --state all --search "<words from the row>") and read its title and body. On zero or many matches, stay with the issue facts.
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 · 115 lines · 48 tokens per session scan A 02b7f58eb776
explain is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,334 once invoked, about $0.0002 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.
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…
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.