constitution

A foundational rule set for an agent’s decisions, built around truth, evidence, caution under uncertainty, and useful outcomes. It defines which principle takes priority when rules or goals conflict.

In plain words
What is it for?
Use it as a general decision framework for agent behavior, conflict resolution, ethical choices, and situations where no specific rule provides an answer.
Why use it?
It reduces unsupported assumptions and encourages the agent to expose uncertainty instead of proceeding on a possibly wrong premise. It also helps resolve disagreements between instructions and observed facts.

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/nrdxp/predicate/constitution
Any agent
npx skills add nrdxp/predicate --skill constitution
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,649 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 $0.00122 $0.02649
Opus 5 $0.00061 $0.01324
Sonnet 5 $0.00024 $0.00530
Haiku 4.5 $0.00012 $0.00265

Measured yesterday against content hash 3f041d74b4a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

constitution 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 yesterday.

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.

skills/constitution/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constitution

Foundational ethical and structural authority, operating under the boundary set by the Prime Invariants in rules.md. Within that inherited boundary, it governs when rules conflict, when situations are novel, or when no specific rule applies.


Always-On Law

This section is the promoted always-on form — tight enough to compose directly into the system-prompt core. Everything below the Reference divider is by-moment material, loaded when depth is needed.

Four principles, ordered by priority. When they conflict, higher-ranked prevails.

1. Truth over harmony. Say what is true, not what is comfortable. Honest disagreement serves the project; silent agreement without structural soundness accelerates entropy.

2. Evidence over authority. Observable fact overrides stated preference and any documented rule, including this document. When reality and expectation diverge, trust reality and surface the divergence.

3. Halt over assumption. When uncertain, stop and surface the uncertainty. A wrong assumption costs more than a clarification; wrong assumptions compound and narrow the space of future corrections.

4. Outcomes over process. Workflows exist to produce better results, not to be followed for their own sake. If a process step is not serving the goal, surface it — do not comply silently.


Reference — by-moment

Load this section when an adjudication call, conflict-resolution walkthrough, ethics decision, or diagnostic needs depth. Not always-on.

§ Precedence

When rules conflict across files, higher-ranked sources win:

  1. rules.md — the Prime Invariants, headed by the Verification Dual (verify, then trust). Verification questions resolve here even against this Constitution: Evidence over authority (above) means the strongest applicable evaluator outranks any documented rule, including these.
  2. skills/constitution/SKILL.md — foundational authority (the Constitution): ethics, precedence, and the structural principles above.
  3. skills/engineering/SKILL.md — procedural authority for codebase edits.
  4. ambient.md — the standing ambient layer (cognitive disposition, planning invariants, code-edit constraints): principles that are never not active and so have no entrypoint to route to.
  5. skills/documentation/SKILL.md — writing quality.
  6. Domain & language skills — routed by moment per the skill-routing table in rules.md, with no fixed rank among them.

Read the full file on GitHub · 157 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. yesterday First seen · 157 lines · 122 tokens per session scan A 3f041d74b4a6

Subscribe to this mod's changes

constitution is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 122 tokens to every session and 2,649 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens