Borrowing it
Nothing to install: this file belongs to ReviewStage/stage-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ReviewStage/stage-cli/main/.agents/skills/trade-off/SKILL.mdgit clone --depth 1 https://github.com/ReviewStage/stage-cliWrote 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/reviewstage/stage-cli/trade-off)<a href="https://agentmods.dev/skills/reviewstage/stage-cli/trade-off"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/trade-off/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/reviewstage/stage-cli/trade-off"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/trade-off.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00186 | $0.02596 |
| Opus 5.5 | $0.00074 | $0.01038 |
| Sonnet 5.5 | $0.00037 | $0.00519 |
| Haiku 4.5 | $0.00019 | $0.00260 |
Grade A, and why
trade-off 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 1mo 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trade-off
Agents over-build by default. They add product behaviors, flows, and UI states that weren't asked for, and they reach for queues, caches, new packages, new tables, and real-time infra when nothing in the task demanded them. The cost is paid forever: more surface area for users to get confused by, more infra to operate, and more code to read, maintain, and change later.
This skill is a forcing function. At any point in the lifecycle of a task — planning, before implementation, or looking back at a diff — identify what could be cut by accepting a reasonable trade-off, and surface those cuts to the user as explicit decisions.
When to use
Invoke this any time complexity is visible. There are three natural moments:
- Planning — sketching what the feature should do. Trade-offs are cheapest here because nothing is built yet; the cut is just "don't design it in."
- Before implementing — a plan exists, you're about to write code. Last chance to cut before the work starts.
- After implementing — reviewing a diff you or another agent just produced. The cut now means deleting code, which is more expensive than not writing it, but still usually worth it.
Signals any of the three applies:
- The task spans multiple UI states, screens, or flows
- There's notification, history, undo, real-time, or bulk behavior on the surface area
- A new behavior is being added that isn't the core ask but felt "natural to include"
- The plan introduces a queue, worker, cache layer, or background job
- The plan adds a new package in the monorepo, a new database table, or a new external service
- The plan uses streaming, websockets, SSE, or other real-time infra
- A migration or backfill is being designed
- A new admin surface or auth surface is being added
- The user's request is short but the scope feels long
- The diff touches multiple files across packages when the ask named one
If the task is genuinely small and concrete and the plan/diff reflects that, skip this skill.
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.
- 1mo ago First seen · 158 lines · 186 tokens per session scan A 2a0ac636959d
trade-off is a skill published in the GitHub repository ReviewStage/stage-cli (274 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,596 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…