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/breakdownnpx skills add a1f/agent-templates --skill breakdowngit 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 | $0.00044 | $0.00571 |
| Opus 5 | $0.00022 | $0.00285 |
| Sonnet 5 | $0.00009 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
breakdown 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 3d 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.
What it actually says
Breakdown
Run the full planning pipeline — PRD → slices → PR breakdown — into one
growing GitHub issue, pausing at each gate. Composes to-prd, to-issues, and
pr-breakdown, each invoked directly.
/breakdown [description or context] [--title="..."] [--label=Plan]
Phase 1: to-prd → creates the issue (gates: clarify, approve)
Phase 2: to-issues → appends slices (gate: discuss)
Phase 3: pr-breakdown → appends PR rows + PR-map artifact (gate: approve)
Run the phases in order; start each only after the previous reports success. The gates live inside each sub-skill — you just relay their results. A sub-skill that ends without its success line declined a gate: stop and report.
Phase 1 — PRD
Invoke to-prd via the Skill tool. Pass the user's [description or context] and
any --title / --label. Capture N from its final line —
PRD published: <url> (issue #N). If to-prd reports a declined gate (no issue
published), stop. If it published but the line won't parse, confirm N with the
user before continuing.
Phase 2 — Slices
Invoke to-issues with --issue=N. It appends the slice plan and reports
Slices appended to issue #N. Proceed on that; stop if it reports a declined gate.
Phase 3 — PR breakdown
Invoke pr-breakdown with --issue=N. It appends the PR rows, publishes the
PR-map artifact, and reports PR breakdown appended to issue #N with the map URL —
relay that URL. Stop if it reports a declined gate.
If a gate is declined or a phase fails
Stop and report. Whatever already completed stays valid: a declined Phase 1 leaves nothing, Phase 2 leaves the PRD, Phase 3 leaves PRD + slices — any is a fine stopping point.
Common mistakes
| Mistake | Fix |
|---|---|
Not threading --issue=N into Phases 2–3 |
Capture N from Phase 1 and pass it on |
| Nesting skills (skill → skill → skill) | Invoke each phase's skill directly |
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.
- 3d ago First seen · 55 lines · 44 tokens per session scan A ac3add350873
breakdown is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 571 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.
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…