second-order

A thinking method that traces what happens after an initial decision or event, including later reactions and side effects.

In plain words
What is it for?
Use it to analyse plans, policies, business decisions, and other changes over time. It helps map immediate, second-, third-, and longer-term consequences.
Why use it?
It helps avoid stopping at the obvious result and missing how people, markets, or systems adapt. It also highlights less visible winners and losers.

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/3243dwon/clear-eye/second-order
Any agent
npx skills add 3243dwon/clear-eye --skill second-order
Clone the repo
git clone --depth 1 https://github.com/3243dwon/clear-eye

Made for: Claude Code, Codex.

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 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 $0.00157 $0.00847
Opus 5 $0.00078 $0.00424
Sonnet 5 $0.00031 $0.00169
Haiku 4.5 $0.00016 $0.00085

Measured 2d ago against content hash 869f06d35189, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

second-order 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.

second-order/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Second-Order Thinking

Most analysis stops at the first consequence. The edge is in the second, third, and long-tail effects — and in who quietly wins or loses once everyone adapts.

Core principle

First-order thinking asks "what happens?" Second-order thinking asks "...and then what? — and then what?"

Every effect becomes a new cause. People and markets react to the first consequence, and the reaction is often where the real story is.

The process

  1. Name the change. State the decision or event precisely.
  2. First order. The immediate, intended effect. (Usually obvious — get it on the table fast.)
  3. Second order. How do the affected parties respond to that first effect? Incentives shift; people route around constraints; prices and behavior adjust.
  4. Third order and beyond. What do those responses cause? Keep asking "and then what?" until the chain goes speculative — then stop and say so.
  5. Winners & losers. After everyone adapts, who is better and worse off? Look hard for the non-obvious ones — the party nobody mentioned.
  6. Reflexivity & time. What second-order effect partially cancels (or amplifies) the first? What only appears over months or years?

Output format

  1. The change — one line.
  2. The cascade — first → second → third, as a short chain (or a couple of chains if it branches). Mark where confidence drops.
  3. Non-obvious winners & losers — the ones first-order analysis misses.
  4. The effect most people will underweight — your single highest-value call.
  5. Confidence — flag which links are solid vs. speculative.

Worked example

Change: A city introduces rent control on large apartment buildings.

First order: Existing tenants in covered units pay less. (Intended.)

Second order: Landlords cut maintenance on price-capped units (margin is squeezed), and some convert rentals to condos to exit the regime. New construction of covered buildings slows — why build what you can't price?

Third order: Rental supply tightens; uncovered and new units get more expensive; mobility drops as tenants cling to below-market leases, which gums up the whole market.

Non-obvious winners/losers: Winners — incumbent long-tenured renters; condo converters; owners of uncovered buildings (pricing power). Losers — newcomers to the city, future renters, and (slowly) the housing stock itself.

Most underweighted effect: The supply chill is invisible for years, then dominant — by the time it's obvious, it's structural.

Confidence: First/second order high (well-documented); third-order magnitude medium.

Read the full file on GitHub · 60 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. 2d ago First seen · 60 lines · 157 tokens per session scan A 869f06d35189

Subscribe to this mod's changes

second-order is a skill published in the GitHub repository 3243dwon/clear-eye (1 stars, last pushed 3mo ago), licensed MIT. It adds 157 tokens to every session and 847 once invoked, about $0.0008 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.