mindit-correctability

A design review of how quickly a change can be detected, reversed, or rolled back if it proves wrong.

In plain words
What is it for?
Use it to assess feature flags, staged releases, A/B tests, telemetry, kill switches, rollback plans, and broad changes such as migrations or pricing updates.
Why use it?
It helps reduce the cost and impact of mistakes by examining monitoring, rollout limits, and recovery options.

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/dragoon0x/usemindit/mindit-correctability
Any agent
npx skills add Dragoon0x/usemindit --skill mindit-correctability
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/usemindit

Made for: Claude Code, Codex.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,147 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 $0.00115 $0.01147
Opus 5 $0.00057 $0.00574
Sonnet 5 $0.00023 $0.00229
Haiku 4.5 $0.00012 $0.00115

Measured 2d ago against content hash 1bdd5cdc4d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mindit-correctability 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 2d 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/mindit-correctability/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mindit-correctability

The eighth of the eight forces. Run this when the question is "if this is wrong, how fast can we find out and how cleanly can we fix it."

The force

Most design decisions are bets. Some bets are right; some are wrong. The cost of being wrong depends on three things: how quickly can the team tell, how broadly does it apply when it's wrong, and how cleanly can they reverse course.

A change behind a 5 percent rollout with a kill switch and rich telemetry is cheap to be wrong about. A change shipped to 100 percent of users with no instrumentation and a destructive data migration is catastrophic to be wrong about.

Correctability asks: given that this decision might be wrong, what is the cost of being wrong, and what mechanisms are in place to recover?

When to run this

  • The user is planning a launch, rollout, or migration.
  • The user mentions A/B tests, feature flags, percentage rollouts, kill switches, or telemetry.
  • The user is about to make a broad-impact change: default change, pricing change, schema migration, brand refresh, design system overhaul.
  • The user uses words like "rollback," "revert," "kill switch," "monitoring," "blast radius."

How to analyze

  1. Identify the decision. What specifically is being shipped? Who is affected? What state changes?

  2. Map the recovery dimensions. For each criterion, ask both "can we" and "have we planned to."

  3. Distinguish "reversible in theory" from "reversible in practice." A change is only practically reversible if the rollback is planned, rehearsed, and instrumented.

  4. Surface the blast radius explicitly. Even good correctability is wasted if the blast is too big. A bad change behind a 100 percent rollout with a working rollback still affected every user for the duration of the rollback.

  5. Check anti-patterns.yaml.

  6. Write the artifact.

Rubric

Criterion Weight What you are scoring
User-side reversibility 0.20 Can users undo what they did inside this design? Cancel, revert, restore, change-of-mind paths.
System-side reversibility 0.20 Can the team roll back the change? Feature flag, deploy revert, data migration reversibility.
Detection latency 0.20 How quickly will the team know if this change is wrong? Telemetry, error tracking, support tickets, business metrics.
Blast radius 0.20 If wrong, how many users does it affect before someone can intervene? 5 percent rollout is small; 100 percent is large.
Pre-commit checks 0.20 What gates does the change pass through before broad release? Internal test, beta cohort, percentage rollout, holdback.

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 79 lines · 115 tokens per session scan A 1bdd5cdc4d38

Subscribe to this mod's changes

mindit-correctability is a skill published in the GitHub repository Dragoon0x/usemindit (2 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 1,147 once invoked, about $0.0006 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