Agent skill

Verify

by jongwony in jongwony/epistemic-protocols

This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure…

MITAuto-check passed

Install Verify

skills CLI
$ npx skills add jongwony/epistemic-protocols --skill verify -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jongwony/epistemic-protocols verify --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jongwony/epistemic-protocols.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/verify .claude/skills/verify && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify
GitHub stars
173
Token cost
~1.4k tokens
SKILL.md length
457 words
Files
14 (incl. scripts, references)
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure…

  • Works in 5 steps: Static Checks → Expert Review → Synthesize Findings → …
  • Asks to verify protocols
  • SKILL.md covers Purpose, Core Principles, Workflow and Severity Reference, plus 4 more sections
  • Runs JavaScript scripts from its folder; calls node

What it does

Verify is an agent skill from jongwony/epistemic-protocols. This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `references/co-change.md`, `references/criteria.md` and `references/review-checklists.md`).

The repository describes itself as: Epistemic protocols for Claude Code — structure human-AI interaction quality at every decision point - https://epistemic-protocols.com. The licence is MIT.

When your agent uses it

  • Asks to verify protocols
  • Check consistency before commit
  • Validate definitions
  • Run pre-commit checks

Example prompts

  • “verify protocols”
  • “check consistency before commit”
  • “validate definitions”
  • “/verify”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash(node *), Task, AskUserQuestion

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Static Checks
  2. Expert Review
  3. Synthesize Findings
  4. Surface via Gate Interaction
  5. Handle User Decision

What it can do on your machine

Read from SKILL.md and the folder at commit af5aa79. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash(node *)
    • Task
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify loads about 1.4k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 457 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jongwony/epistemic-protocols at commit af5aa79, republished under its MIT licence (© jongwony). 457 words, ~1,431 tokens.

Download SKILL.mdSave it as .claude/skills/verify/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
verify
description
This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.
allowed-tools
Read, Grep, Glob, Bash(node *), Task, AskUserQuestion

Protocol Verification

Verify epistemic protocol consistency before commit through static checks and expert review.

Purpose

Surface potential issues in protocol definitions without blocking commits. Follow Anthropic philosophy: transparency over enforcement, user agency over automation.

Core Principles

PrincipleImplementation
Surface, don't enforcePresent findings; user decides action
Zero-context scriptsStatic checks run without consuming context
Explicit controlUser invokes /verify intentionally
Graduated severityCritical / Concern / Note categorization

Workflow

Phase 1: Static Checks

Run scripts/static-checks.js against project root. This script executes without loading into context.

bash
node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}

Output format:

json
{
  "pass": [{ "check": "...", "file": "...", "message": "..." }],
  "fail": [{ "check": "...", "file": "...", "message": "..." }],
  "warn": [{ "check": "...", "file": "...", "message": "..." }]
}

Checks performed: scripts/static-checks.js is the orchestrator. Its head names the layer files it runs and what each layer holds, and each layer file's CHECKS list is that layer's inventory. references/verification.md carries why the non-obvious checks exist and what to do when one fires.

Phase 2: Expert Review

Spawn parallel Task subagents for LLM-based review — one per perspective (Type Theory / Category Theory, Instruction Design, Claude Code Ecosystem). Load each subagent's prompt template from references/review-checklists.md (single source of truth; do not duplicate the templates here — see Review Checklists below). Each template samples the protocols changed in the current diff, falling back to a representative sample when the diff is not protocol-scoped.

All three subagents run in parallel. Collect results before proceeding.

Phase 3: Synthesize Findings

Combine static check results with expert review findings. Categorize by severity:

SeverityStatic Check SourceLLM Review Source
Criticalfail arrayfindings with severity: "critical"
Concernwarn array (structural)findings with severity: "concern"
Notewarn array (stylistic)findings with severity: "note"

Identify convergence (all perspectives agree) and divergence (perspectives differ).

Apply Claude Code Ecosystem expert's filtered array to dismiss false positives from other perspectives.

Show full SKILL.md (185 more words)Show less
Phase 4: Surface via Gate Interaction

Present findings via gate interaction. Format:

## Verification Results

### Critical (n issues)
- [issue 1]: [location] - [description]
- [issue 2]: [location] - [description]

### Concerns (n issues)
- [issue 1]: [location] - [description]

### Notes (n observations)
- [observation 1]

### Filtered (Claude Code context)
- [filtered issue]: [reason dismissed]

---
Select action:

Options to present:

  1. Fix critical issues - Address critical findings before commit
  2. Review concerns - Examine each concern individually
  3. Proceed anyway - Commit with decision logged
  4. Cancel - Abort verification
Phase 5: Handle User Decision
DecisionAction
Fix criticalShow specific fixes, await approval for each
Review concernsPresent concerns one by one with dismiss/address options
Proceed anywayLog decision, suggest commit message annotation
CancelEnd verification, no changes

Commit message annotation (if proceeding with issues):

[verify: n critical, m concerns acknowledged]

Severity Reference

Consult references/criteria.md for which channel judges which kind of obligation, the severity definitions, and what review reads for.

Review Checklists

Consult references/review-checklists.md for:

  • Type Theory / Category Theory expert prompt template
  • Instruction Design expert prompt template
  • Claude Code Ecosystem expert prompt template
  • Known issues checklist
  • Synthesis template

Error Handling

ErrorResponse
Script execution failsReport error, offer manual check option
Subagent timeoutReport partial results, continue with available data
No issues foundConfirm clean state, proceed to commit

Integration Notes

Standalone Usage

Most common pattern: invoke /verify before /commit command.

Output Examples

Clean State
## Verification Results

All checks passed.

- Static checks: all checks pass (0 fail, 0 warn)
- Type/Category review: No issues
- Instruction Design review: No issues

Ready to commit.
Issues Found
## Verification Results

### Critical (1 issue)
- State machine totality: hyphegesis/skills/conduct/SKILL.md - Undefined transition when the person withdraws after the method was handed off

### Concerns (2 issues)
- Categorical terminology: hyphegesis/skills/conduct/SKILL.md - limit/colimit may not match intended semantics
- Directive verb: hyphegesis/skills/conduct/SKILL.md - "Invoke AskUserQuestion" should be "call"

### Notes (1 observation)
- Version: hyphegesis plugin.json version not bumped since last change

---
How to proceed?

© jongwony, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references) in .claude/skills/verify of jongwony/epistemic-protocols.

  • SKILL.md
  • references/co-change.md
  • references/criteria.md
  • references/review-checklists.md
  • references/verification.md
  • scripts/artifact-self-containment.js
  • scripts/artifact-sync.js
  • scripts/check-context.js
  • scripts/language-purity.js
  • scripts/lean-bridge.js
  • scripts/lean-contract.js
  • scripts/prose-surface.js
  • scripts/static-checks.js
  • scripts/static-checks.test.mjs

Open the folder on GitHubat commit af5aa79

More from jongwony/epistemic-protocols

All 29 skills in this repo
  • Outcome

    jongwony/epistemic-protocols

    This skill should be used when the user asks to "run the outcome eval", "paired bare vs protocol", "which decisions did the protocol surface", "count what the AI asked or presented", "does /inquire…

    173 GitHub stars~1.3k tokensUpdated today
    Auto-check: notes
  • Realize

    jongwony/epistemic-protocols

    This skill should be used when the user asks to "run the eval", "test whether the protocol actually works at runtime", "check type realization", "measure protocol fulfillment", "run the…

    173 GitHub stars~3.3k tokensUpdated today
    Auto-check: notes
  • Encapsulation

    jongwony/epistemic-protocols

    This skill should be used when the user asks to "audit plugin encapsulation", "check self-containment semantics", "find contributor-knowledge assumptions", or invokes /encapsulation.

    173 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Formal Review

    jongwony/epistemic-protocols

    This skill should be used when the user asks to "formal review", "formal lens review", or invokes /formal-review.

    173 GitHub stars~3.5k tokensUpdated today
    Auto-check: notes
  • Recollect

    jongwony/epistemic-protocols

    The user vaguely recalls something discussed before but cannot name it — one session, or a line of work, topic, or settled concept across several: find it in past records to recognize.

    173 GitHub stars~8.7k tokensUpdated today
    Auto-check passed
  • White Bear

    jongwony/epistemic-protocols

    A skill your agent uses when the user asks to "check white bear", "audit prohibitions", "find negative framing", or invokes /white-bear.

    173 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

Questions about Verify

What does Verify do?

This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure…. Verify is an agent skill from jongwony/epistemic-protocols. This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality.

When should I use Verify?

Verify fits situations like: asks to verify protocols; check consistency before commit; validate definitions; run pre-commit checks.

How do I install Verify in Claude Code?

Run `npx skills add jongwony/epistemic-protocols --skill verify -a claude-code`. Or copy the skill folder (.claude/skills/verify in jongwony/epistemic-protocols) into .claude/skills/verify in your project. Claude Code loads it when a task matches its description.

How do I install Verify in Codex?

Run `npx skills add jongwony/epistemic-protocols --skill verify -a codex`. Or copy the skill folder (.claude/skills/verify in jongwony/epistemic-protocols) into .agents/skills/verify in your project. Codex loads it when a task matches its description.

Can I use Verify in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jongwony/epistemic-protocols --skill verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify, .gemini/skills/verify, .github/skills/verify and .opencode/skills/verify in your project.

What does Verify need to run?

Going by SKILL.md and its folder, Verify needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash(node *), Task, AskUserQuestion.

Does Verify access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Verify safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Verify use?

Verify is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.

Who maintains Verify?

jongwony (a GitHub user) maintains it in jongwony/epistemic-protocols, which has 173 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 8, 2026.

Source: jongwony/epistemic-protocols on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.