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/make-pr-litenpx skills add a1f/agent-templates --skill make-pr-litegit 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/make-pr-lite)<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>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 | $0.00100 | $0.03194 |
| Opus 5 | $0.00050 | $0.01597 |
| Sonnet 5 | $0.00020 | $0.00639 |
| Haiku 4.5 | $0.00010 | $0.00319 |
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.
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.mdlives in; it holds only the SKILL.md itself. The rule files and the runtimegates/are resolved fromextras_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'srules/andgates/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 — useWriteonly for theevidence/<branch-slug>/handoff at Done (branch-slug= the pushed branch with/and whitespace →_— the key/pr-explainjoins 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>.jsonby the task's language(s) /allowed_paths. After the coder runs, re-check againstgit diff --name-only <base>...HEAD. A changed language with no profile → stop and report. - rules to pass — always
design-principles.md;comments.mdtocoder-liteand the comment-reviewer only (comments are not the 3 reviewers' lens);tdd.mdfor behavioral work; the language rule (python.md/typescript.md/rust.md) per changed file type.
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 · 174 lines · 100 tokens per session scan A eddc15855145
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.
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…