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/dragoon0x/usemindit/mindit-consequencenpx skills add Dragoon0x/usemindit --skill mindit-consequencegit clone --depth 1 https://github.com/Dragoon0x/useminditWhat 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 | $0.00124 | $0.01165 |
| Opus 5 | $0.00062 | $0.00583 |
| Sonnet 5 | $0.00025 | $0.00233 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
mindit-consequence 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mindit-consequence
The fourth of the eight forces. Run this when the question is "what does this foreclose, and what does it open."
The force
Every design decision opens some doors and closes others. Some closures are visible: a destructive delete button removes data. Most closures are invisible: a choice of data model now means a redesign in six months. A default that nudges 70 percent of users one direction shapes the company's product strategy. A consent flow written today defines what the company can do with user data forever.
Consequence asks: of the doors this design closes, which ones did the team know they were closing?
When to run this
- The user is about to ship a destructive flow (deletion, cancellation, payment, account changes).
- The user is choosing a default (default sort order, default privacy setting, default plan).
- The user mentions data: what gets stored, what gets exposed, who can see it, how long it is kept.
- The user uses words like "irreversible," "side effect," "knock-on," "future," "blocks us from," or "locks us in."
- The user is choosing between two architectures or two information models and asks for a review.
How to analyze
-
Surface the action. What does this design do? What does it cause to happen, both immediately and downstream? Write it out plainly.
-
Walk the five dimensions. For each criterion below, ask: what is this design closing or opening on this axis?
-
Look for invisible closures. Most consequence failures are not in the obvious "delete account" button. They are in defaults, in data models, in what the design assumes the next feature can do.
-
Surface unmade decisions. "What happens if the user changes their mind in three months" is often unmade. Surface it. Do not invent the answer.
-
Check
anti-patterns.yaml. -
Write the artifact.
Rubric
| Criterion | Weight | What you are scoring |
|---|---|---|
| Reversibility | 0.20 | Can the user undo what this design lets them do? Within what time window? With what cost? |
| Path foreclosure | 0.20 | Does this design make other user paths harder, slower, or impossible? (Often by adding friction to one path or removing it entirely.) |
| Data implications | 0.20 | What gets stored as a result of this design? Who can see it? How is it deleted? Is the answer to all three known? |
| Future-design lock-in | 0.20 | Does this design constrain what the team can do in the next version? (Information architecture, naming, defaults, data shape.) |
| Second-order effects | 0.20 | What knock-on effects on adjacent features, the support team, the data team, or other surfaces? |
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.
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.
- 2d ago First seen · 78 lines · 124 tokens per session scan A e85b5a206594
mindit-consequence is a skill published in the GitHub repository Dragoon0x/usemindit (2 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,165 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.