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 skills add jonZlotnik/how-to-agent --skill reversible-decisionsgit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/reversible-decisions)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/reversible-decisions"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/reversible-decisions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/reversible-decisions"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/reversible-decisions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.00624 |
| Opus 5 | $0.00028 | $0.00312 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
reversible-decisions 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 10d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reversible Decisions
There are no final decisions, only decisions whose reversal you have or haven't planned for. When two options are otherwise comparable, choose the one you can back out of cheaply. When you must take an irreversible step, do it deliberately — with the exit door documented.
When to use
- Selecting a framework, database, queue, vendor, or third-party service
- Defining a public API, on-disk format, or migration that touches stored data
- Naming a concept that will spread through the codebase
- About to say "we'll always need this" or "we'll never need that"
Protocol
- Rate reversibility on a 1–5 scale: 1 = revert in a commit, 5 = company-wide migration. Write the number down.
- Compare options on cost-to-undo, not only cost-to-adopt. A 2-week build that's a 3 to reverse usually beats a 1-week build that's a 5.
- Document the exit door. What concrete steps reverse this? Who would do them? What signals would tell us we need to?
- Add abstraction only where reversal is plausible. Don't wrap everything; do wrap the things you flagged as 4–5.
- Name and date the decision in the codebase (ADR, doc, or comment) so future-you knows it was deliberate.
Worked example
Choosing a search backend. Options: Postgres full-text (cost-to-undo: 1, just drop the index) vs. managed Elasticsearch (cost-to-undo: 4, migrate data, rewrite queries, change deploy). Both adequate at current scale. Pick Postgres now; the exit door to Elasticsearch is "wrap search behind a SearchIndex trait with one method". Postgres day-one, swap later if scale demands. Reversal cost paid once, in the abstraction, instead of in panic.
Red flags (rationalizations to reject)
- "We need to make this decision now and forever." — Almost no decision is forever. The framing is usually false urgency.
- "It would be wasteful to abstract this." — Cheap abstractions on high-cost-to-undo decisions pay for themselves the first time.
- "Switching costs aren't our problem yet." — They never are, until they are, and then they're enormous.
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.
- 10d ago First seen · 40 lines · 57 tokens per session scan A 04810875ed1d
reversible-decisions is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 624 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…