boundary

Validates and refines Initial Boundary Condition prompts against seven sufficiency conditions before dispatch.

10|2|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/nrdxp/predicate --skill boundary-nrdxp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: boundary
Source: https://github.com/nrdxp/predicate/tree/main/skills/boundary
Command: npx skills add https://github.com/nrdxp/predicate --skill boundary-nrdxp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Prompts sent to expensive or autonomous AI agents often fail late and expensively because the task frame was never verified. This Skill defines normative sufficiency conditions for Initial Boundary Conditions (IBCs) and a cheap-tier adversarial refinement loop that catches bad frames before an expensive walk launches. ## Core Features & Use Cases - Seven Sufficiency Conditions (S1–S7): Checkable criteria covering falsifiable premises, rejection genres, decision rights (RESOLVED/DELEGATED/RESERVED), evaluator attachment, verbatim context curation, amendment protocols, and discipline proportion. - Boundary Refinement Loop (/boundary): A DRAFT → ATTACK → REVISE → APPROVE → DISPATCH cycle using isolated cheap-tier adversarial reviewers whose objections must cite a violated condition and evidence. - Comprehension Probe: A zero-context dry run where a cheap agent produces a plan from only the IBC, surfacing unanswered questions, plan-vs-intent divergence, and canary-trap bites before dispatch. - Use Case: Before dispatching an autonomous worker on a multi-hour coding campaign, run the refinement loop and probe to confirm the IBC's premises are verifiable, its decision rights are partitioned, and a human has approved the fixed-point IBC*. ## Quick Start Ask the agent to audit this task prompt against the boundary sufficiency conditions and run the refinement loop until it is ready to dispatch.

Frequently Asked Questions about boundary

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate a prompt before sending it to an expensive AI model?

Check the prompt against the seven sufficiency conditions: falsifiable premises, a defined rejection genre, partitioned decision rights, evaluators attached to every constraint, verbatim context pointers, an amendment protocol, and discipline proportioned to walker capability. Then run adversarial review until zero grounded objections remain.

What is an Initial Boundary Condition in AI agent workflows?

An Initial Boundary Condition (IBC) is the prompt contract that launches an agent run: the goal, constraints, and acceptance criteria. A sufficient IBC makes failure cheap and early by giving the agent verifiable premises and an explicit low-cost path to reject a bad frame.

How does the boundary refinement loop work?

The loop cycles DRAFT, ATTACK, REVISE, APPROVE, DISPATCH. Cheap-tier adversarial reviewers in isolated contexts raise objections that must cite a sufficiency condition and evidence; the loop converges when a sweep yields zero grounded objections, then a human approves dispatch.

When should I not run the full boundary refinement loop?

Skip the loop for mechanical steps inside a frame the human already approved; per decision DG1, approval attaches to the agreed frame, not each IBC. The loop runs only where the goal is open, premises are unverified, or the walk could diverge from what was agreed.

Why do AI agents fail on well-written prompts?

Capable agents fail through confidently-wrong frames: they build large coherent structures on false premises without local error signals. The fix is premise verification before dispatch, using falsifiable claims and a comprehension probe that simulates the consumer with zero context.