make-pr-lite

make-pr-lite is a skill for Claude Code, Codex from a1f/agent-templates. It costs 100 tokens per session (3,194 once invoked), scanned A, original, MIT.

A workflow for finishing an already-scoped, low-risk pull request (PR), which is a proposed code change for review. It coordinates one coder, automated checks, and several reviewers, then combines the result into one commit.

In plain words
What is it for?
Use it for small changes such as argument handling, parsing, data models, read-only views, configuration, or combining existing tested components.
Why use it?
It reduces the work of coordinating coding, tests, checks, and review for a small change. It is not intended for changes involving data deletion, file overwrites, or other high-risk behavior.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/a1f/agent-templates/make-pr-lite
Any agent
npx skills add a1f/agent-templates --skill make-pr-lite
Clone the repo
git clone --depth 1 https://github.com/a1f/agent-templates

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for make-pr-lite

README.md
[![agentmods](https://agentmods.dev/badge/skills/a1f/agent-templates/make-pr-lite.svg)](https://agentmods.dev/skills/a1f/agent-templates/make-pr-lite)
Your own site
<a href="https://agentmods.dev/skills/a1f/agent-templates/make-pr-lite"><img src="https://agentmods.dev/badge/skills/a1f/agent-templates/make-pr-lite.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00100 $0.03194
Opus 5 $0.00050 $0.01597
Sonnet 5 $0.00020 $0.00639
Haiku 4.5 $0.00010 $0.00319

Measured 3d ago against content hash eddc15855145, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-pr-lite 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.

skills/make-pr-lite/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

make-pr-lite

You orchestrate one already-scoped, low-risk PR to done: dispatch the agents, run the gates, judge the panel, decide. You never write production code or tests.

Use it for / route elsewhere

Use for greenfield or low-risk PRs: arg routing, parsing, models, read-only views, config, or code that only composes already-tested units and adds no new state mutation.

High-risk set → recommend /make-pr and stop (proceed only if the human explicitly confirms lite for this task): filesystem/state mutation, destructive ops (delete, overwrite, .bak restore), JSON/settings merge-and-unmerge, refcounting, content-hash/drift, or a cutover touching existing behavior. (Lite verifies a RED's reason but never re-witnesses it live; only /make-pr guarantees that.)

Runtime resolution

  • skill_root — the directory this SKILL.md lives in; it holds only the SKILL.md itself. The rule files and the runtime gates/ are resolved from extras_root, not from here.
  • extras_root — the installer's state root ~/.claude/at, the single source of truth the installer stages a package's extras into — this skill's rules/ and gates/ live here. Resolving them from this one root keeps an install self-contained, with no dependency on a repo checkout.
  • rules_root~/.claude/at/rules, the rules the installer composes from the single canonical source; pass rule files as absolute paths (a subagent's cwd is the target repo, so bare names won't resolve).
  • target_cwd — the repo being changed; run every git/gate command there.
  • run_root<target_cwd>/.v1-runs, writable; lite keeps no JSONL log — use Write only for the evidence/<branch-slug>/ handoff at Done (branch-slug = the pushed branch with / and whitespace → _ — the key /pr-explain joins on).
  • base — user/spec-named → else git merge-base HEAD origin/main → else … main → else stop and ask.
  • gates — preflight: pick ~/.claude/at/gates/<lang>.json by the task's language(s) / allowed_paths. After the coder runs, re-check against git diff --name-only <base>...HEAD. A changed language with no profile → stop and report.
  • rules to pass — always design-principles.md; comments.md to coder-lite and the comment-reviewer only (comments are not the 3 reviewers' lens); tdd.md for behavioral work; the language rule (python.md/typescript.md/rust.md) per changed file type.

Read the full file on GitHub · 174 lines

Changes

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.

  1. 3d ago First seen · 174 lines · 100 tokens per session scan A eddc15855145

Subscribe to this mod's changes

make-pr-lite is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 3,194 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens