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/tweekfawkes/prompts/newestcodenpx skills add TweekFawkes/prompts --skill newestcodegit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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/tweekfawkes/prompts/newestcode)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/newestcode"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/newestcode.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 | $0.00162 | $0.02892 |
| Opus 5 | $0.00081 | $0.01446 |
| Sonnet 5 | $0.00032 | $0.00578 |
| Haiku 4.5 | $0.00016 | $0.00289 |
Grade A, and why
newestcode 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/newestcode — Sync this checkout with the latest merged code
Other agents and the user merge PRs to main constantly. Work that started an hour ago may now be sitting on stale code. Your job: make THIS checkout reflect the latest origin/main, safely, and tell the user exactly what changed — then, if the running environment needs to match, offer to redeploy.
This is the download counterpart to the repo's "upload" skills. Don't confuse them:
/openpr,/landtomain,/gohomepush this branch's work up tomain./newestcode(this skill) pulls the world's latestmaindown into wherever we are. It creates no feature work and opens no PR.
The whole skill is built around one rule: never destroy or orphan local work to get newer code. A dirty tree, local commits, or a conflict means stop and surface, not force through.
Authoritative facts (verify, don't assume)
- Remote:
origin→ your GitHub repo. Confirm withgit remote -v. - Integration branch:
main. If PRs merge as merge commits titledMerge pull request #N from <branch>,git log HEAD..origin/mainreads as a clean list of the PRs you're about to pull in. - One
.git, many worktrees.git fetchhere updatesorigin/*for every worktree at once. Butmainis only ever checked out in ONE worktree (the canonicalmaincheckout); every other worktree is on a feature/detached ref. The right integration move depends on which you're in — that's the phase-3 matrix. - "Latest code" has two layers. (a) The tracked files in this checkout matching
origin/main— always in scope. (b) The thing actually running (your deployed dev environment, and your local virtualenvs) matching that code — only as fresh as the last deploy / dependency sync. Pulling commits fixes (a); it does not fix (b). Phase 5 bridges the gap. - Deploy source is the checkout it's RUN FROM. If your dev deploy syncs the repo copy it runs from onto the dev environment, a redeploy from a feature worktree silently reverts dev to that branch. Only offer the redeploy phase when on the canonical
maincheckout, unless the user explicitly wants this branch on dev. - Gitignored deploy artifacts are not "work." Seeded env files and per-worktree dependency/build caches don't show in
git statusand are reproducible — never force-add them or treat them as something to rescue.
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 · 134 lines · 162 tokens per session scan A bc8c89f113de
newestcode is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 162 tokens to every session and 2,892 once invoked, about $0.0008 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…