realize

realize is a skill for Claude Code, Codex from jongwony/epistemic-protocols. It costs 86 tokens per session (2,039 once invoked), scanned A, original, MIT.

A test procedure for checking whether a protocol's written steps actually happen during a live agent run. It records and grades the run across models and test conditions.

In plain words
What is it for?
Running protocol evaluation cases, collecting JSONL traces, checking whether branches reach their required stopping points, and identifying judgments that still need human review.
Why use it?
Written rules and static checks do not prove that an agent follows the required transitions when working.

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/jongwony/epistemic-protocols/realize
Any agent
npx skills add jongwony/epistemic-protocols --skill realize
Clone the repo
git clone --depth 1 https://github.com/jongwony/epistemic-protocols

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for realize

README.md
[![agentmods](https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/realize.svg)](https://agentmods.dev/skills/jongwony/epistemic-protocols/realize)
Your own site
<a href="https://agentmods.dev/skills/jongwony/epistemic-protocols/realize"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/realize.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,039 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 5.1 $0.00086 $0.02039
Opus 5 $0.00043 $0.01019
Sonnet 5 $0.00017 $0.00408
Haiku 4.5 $0.00009 $0.00204

Measured 5d ago against content hash c172e2e79bff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

realize 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 5d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (evals/scaffold.sh, scripts/harness.mjs, scripts/harness.test.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/realize/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Type Realization

Measure whether one named protocol skill's declared contract is realized during an actual run. The first argument is required; /realize inquire selects only the registered inquire cases and graders. An unknown or omitted target fails before setup.

Purpose

A protocol's formal blocks are runtime-normative: TYPES, PHASE TRANSITIONS, TOOL GROUNDING and the Rules type the prose and carry the operational contract. Static checks establish that a SKILL.md contains those blocks and enforce a bounded set of structural invariants. Nothing establishes that a run follows their transitions.

This skill supplies evidence for that gap. It drives Claude Code or Codex across a matrix of models and treatments, captures the JSONL trace, grades the deterministically observable subset, and names the transcript judgments still owed. A complete automatic cell can establish that collection occurred, the declared branch reached Stop, or the zero-uncertainty branch reached Proceed; semantic ordering and rendered type coverage remain manual until their specified judges are built.

Judgment boundary

The object of judgment is the formal transition trace:

X → context sufficiency → evidence collection as needed → residual deficit
  → formal branch → Stop | Proceed

Every score attaches to a node or edge in that trace. Once the selected branch is observable, judgment ends. A plan, implementation, analysis, or other downstream artifact is evidence that Proceed occurred; its quality, correctness, completeness, and usefulness are outside /realize. Likewise, an unchanged substrate is evidence of Stop only where the case granted the capability to proceed and the formal branch required stopping. references/grader-design.md carries the witness design and the separate oracle that artifact-quality evaluation would require.

When it applies

Reach for this after changing a protocol's phase structure, terminal conditions, gate definition, or answer types — the places where a contract can become unrealizable without any static check noticing. Reach for it also when adopting a new model, where the question is whether the contract still holds on it.

Read the full file on GitHub · 184 lines

Files

What ships with it

25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 184 lines · 86 tokens per session scan A c172e2e79bff

Subscribe to this mod's changes

realize is a skill published in the GitHub repository jongwony/epistemic-protocols (160 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,039 once invoked, about $0.0004 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 2026-08-30.