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/pr-breakdownnpx skills add a1f/agent-templates --skill pr-breakdowngit clone --depth 1 https://github.com/a1f/agent-templatesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/a1f/agent-templates/pr-breakdown)<a href="https://agentmods.dev/skills/a1f/agent-templates/pr-breakdown"><img src="https://agentmods.dev/badge/skills/a1f/agent-templates/pr-breakdown.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00055 | $0.02284 |
| Opus 5 | $0.00028 | $0.01142 |
| Sonnet 5 | $0.00011 | $0.00457 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
pr-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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Breakdown
Break the slice plan in a PRD issue into small PRs (~35 counted lines each) and keep two views of them: a table in the same issue, one row per PR, and a PR map — a private claude.ai artifact laying the PRs out as waves, with blocked-by edges and a card per PR.
The table is the source of truth — the map is drawn from it every run. Status comes
from GitHub — the table caches each PR's #NN and the state it last saw.
/pr-breakdown [--issue=N]
1. Read the issue — plan, existing rows, existing map
2. Write the PR rows
3. Discuss and approve (gate)
4. Draw and publish the map
5. Write it back to the issue
Phase 1 — Read the issue
Use --issue=N if given; else scan the conversation for the last
PRD published: ... (issue #N) line, or ask. Confirm an auto-detected number. Read the
body with gh issue view N --json body -q .body.
No ## Build plan section → stop and tell the user to run /to-issues first.
The slices are that section's table: each row's What and Blocked by seed the PRs, its
Demoable as seeds their Done when, and its Mode (AFK / HITL) says whether it
needs the human. No slicing — single PR instead of a table means one slice, one PR.
From an existing ## PR breakdown, keep two things: the rows (Phase 2 builds on them)
and the map URL in <!-- pr-breakdown:map url=<url> --> (Phase 4 updates that same
artifact).
Phase 2 — Write the PR rows
Split each slice into PRs — one cohesive, reviewable, demoable change each, foundations
before the PRs that use them. Budget each PR at ~35 counted lines — added lines
excluding tests, lockfiles, and generated output, with prose (.md, docs) counted apart.
A PR the size gate will not pass is a PR you must split now: over 50 counted lines is
unlandable once it touches 3+ files, over 100 on 1–2 files, over 150 of prose. Estimate
high: a row you guess at 40 lands at 60. More, smaller rows are always the right answer. Rows only: no coder
prompts (module boundaries, acceptance criteria) — those come later, one PR at a time.
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.
- 4d ago First seen · 166 lines · 55 tokens per session scan A 12257726ef5b
pr-breakdown is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 2,284 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…