second-order — Claude Code command: what it does, how to install
Runs second-order thinking on an action or the current conversation to trace downstream consequences before you commit to changes.
MIT ★ 1,988 updated 2026-04-01
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resourcesWhat second-order does
This command pushes Claude Code beyond immediate first-order outcomes. Instead of stopping at obvious results, it repeatedly asks "And then what happens?" to uncover downstream fallout. The prompt maps initial effects, follows them into second- and third-order layers, and flags delayed repercussions.
The structured process runs through six steps: defining the action, spotting immediate outcomes, tracing causal chains, evaluating delayed costs, and reassessing viability. Running the command without arguments applies this evaluation directly to your active chat context.
The resulting report highlights unintended feedback loops, helping you catch proposals that look acceptable initially but degrade the system over time.
What it helps with
- trace cascading risks before refactoring
- uncover delayed technical debt in architectural choices
- detect negative feedback loops in workflow changes
- re-evaluate feature proposals across multiple causal layers
Example prompts for the agent
- /second-order Switch from REST to GraphQL
- /second-order Remove caching layer to simplify state
- /second-order
How to install second-order
1Plugin marketplace
/plugin marketplace add glittercowboy/taches-cc-resources/plugin install taches-cc-resources@taches-cc-resources2Manually: put the files in place
.claude/commands/second-order.mdCall it with /second-order. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/second-order.mdCall it with /prompts:second-order. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/second-order.prompt.mdManually: put the files in place
.gemini/commands/second-order.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about second-order
How to install second-order in Claude Code?
Register the marketplace repository with /plugin marketplace add glittercowboy/taches-cc-resources, then run /plugin install taches-cc-resources@taches-cc-resources. Alternatively, save the file manually to .claude/commands/second-order.md.
What does the second-order command do?
It systematically evaluates consequences beyond initial effects. The command maps first-, second-, and third-order impacts alongside delayed costs to decide whether an action remains viable.
Can I run second-order without passing an argument?
Yes. If left blank, the command automatically uses the active conversation in Claude Code as the subject for its causal analysis.
Source text
second-order.md · MIT
--- description: Think through consequences of consequences argument-hint: [action or leave blank for current context] --- <objective> Apply second-order thinking to $ARGUMENTS (or the current discussion if no arguments provided). Ask: "And then what?" First-order thinking stops at immediate effects. Second-order thinking follows the chain. </objective> <process> 1. State the action or decision 2. Identify first-order effects (immediate, obvious consequences) 3. For each first-order effect, ask "And then what happens?" 4. Continue to third-order if significant 5. Identify delayed consequences that change the calculus 6. Assess whether the action is still worth it after full chain analysis </process> <output_format> **Action:** [what's being considered] **First-Order Effects:** (Immediate) - [Effect 1] - [Effect 2] **Second-Order Effects:** (And then what?) - [Effect 1] → leads to → [Consequence] - [Effect 2] → leads to → [Consequence] **Third-Order Effects:** (And then?) - [Key downstream consequences] **Delayed Consequences:** [Effects that aren't obvious initially but matter long-term] **Revised Assessment:** After tracing the chain, this action [is/isn't] worth it because... </output_format> <success_criteria> - Traces causal chains beyond obvious effects - Identifies feedback loops and unintended consequences - Reveals delayed costs or benefits - Distinguishes actions that compound well from those that don't - Prevents "seemed like a good idea at the time" regret </success_criteria>
© Lex Christopherson · MIT · glittercowboy/taches-cc-resources