day-one-patch

day-one-patch is a skill for Claude Code, Codex from cenconq25/claude-code-app-studio. It costs 56 tokens per session (1,681 once invoked), scanned A, original, MIT.

A focused patch process for fixing serious, reproducible problems found between a release candidate and public launch. It treats the work as a small sprint with testing and a rollback plan.

In plain words
What is it for?
Use it to scope, implement, test, and release urgent launch fixes from bugs, review feedback, or monitoring alerts.
Why use it?
It helps teams decide which late issues are safe and important enough to fix before users see the release.

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/cenconq25/claude-code-app-studio/day-one-patch
Any agent
npx skills add cenconq25/claude-code-app-studio --skill day-one-patch
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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 day-one-patch

README.md
[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/day-one-patch.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/day-one-patch)
Your own site
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/day-one-patch"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/day-one-patch.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00056 $0.01681
Opus 5 $0.00028 $0.00840
Sonnet 5 $0.00011 $0.00336
Haiku 4.5 $0.00006 $0.00168

Measured today against content hash ebf6e85d5341, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

day-one-patch 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 today.

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.

.claude/skills/day-one-patch/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Day-One Patch

Between the build that went to certification and the build users see at launch, problems show up — late-breaking telemetry, a cert reviewer finding, a marketing copy change. This skill scopes a focused mini- sprint patch, runs it through QA, and lands it on the user before they even notice the gap.


Phase 1: Source the Patch Scope

Resolve the source build:

  • --from=<release-tag> -> read that tag.
  • Otherwise consult production/releases/release-checklist-*.md for the latest release version and use its tag.

Source the candidate patch list from any of:

  • --bug-list=<paths> -> explicit list.
  • Recent BUG records filed since the release tag in production/qa/bugs/.
  • Recent S1/S2 issues triaged in production/qa/triage-*.md.
  • App Store / Play review feedback (if pasted by user).
  • Late-breaking telemetry alerts (Sentry / Crashlytics digest).

Render the candidate list with severity, frequency (if known), and origin source.


Phase 2: Filter to Day-One Scope

Apply the day-one bar — only fixes that meet ALL of these qualify:

  • Severity S1 or S2.
  • Reproducible.
  • Fix is small (< 2 days of engineering, ideally < 1).
  • Fix is low-risk (touches a small, well-understood area).
  • Fix has a regression test plan.

Any candidate failing the bar is either downgraded to a normal sprint, escalated to /hotfix, or rejected.

Use AskUserQuestion to confirm scope:

question: "Day-one scope candidates (top severity first):"
options:
  - "Accept the proposed scope"
  - "Add: [user provides]"
  - "Drop: [user provides]"
  - "Cancel — these are not day-one items"

Phase 3: Risk Assessment

For the agreed scope, run the patch-risk checklist:

  • Each fix has a clear blast radius (which features, which user cohort).
  • Combined diff stays under [project threshold, default 500 LOC].
  • No fix changes the public API surface.
  • No fix changes the on-disk data schema.
  • No fix touches payment flow without a payments specialist on review.
  • No fix touches auth flow without a security review.
  • No fix is bundled with a feature change — patch is fixes only.

Read the full file on GitHub · 255 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. today First seen · 255 lines · 56 tokens per session scan A ebf6e85d5341

Subscribe to this mod's changes

day-one-patch is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,681 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 2026-09-03.

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