validate-graph

validate-graph is a command for Claude Code from tobiasosborne/alethfeld. It costs 13 tokens per session (697 once invoked), scanned A, original, MIT.

A validator for Alethfeld semantic proof graphs, EDN files that describe claims, supporting steps, and their relationships. It checks the file against the project's schema and meaning-level rules.

In plain words
What is it for?
Use it with an EDN proof-graph file to run the Alethfeld validator and interpret its success, validation-error, or file-error result.
Why use it?
It identifies malformed proof data, invalid node properties, and broken semantic relationships before the graph is used. Verbose output helps explain validation failures.

Command for Claude Code

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 commands/tobiasosborne/alethfeld/validate-graph
Clone the repo
git clone --depth 1 https://github.com/tobiasosborne/alethfeld

Made for: Claude Code.

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 validate-graph

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/validate-graph.svg)](https://agentmods.dev/commands/tobiasosborne/alethfeld/validate-graph)
Your own site
<a href="https://agentmods.dev/commands/tobiasosborne/alethfeld/validate-graph"><img src="https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/validate-graph.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 697 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 $0.00013 $0.00697
Opus 5 $0.00006 $0.00349
Sonnet 5 $0.00003 $0.00139
Haiku 4.5 $0.00001 $0.00070

Measured 5d ago against content hash bdf8af917f38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

validate-graph 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.

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/commands/validate-graph.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Proof Graph Validator

Validate EDN proof graph files against the Alethfeld protocol schema and semantic invariants.

Input

The user will provide a file path to an EDN proof graph (.edn). If no path is provided, prompt for one or search for .edn files in the current directory.

Validation Protocol

1. Run the Validator

./cli/scripts/alethfeld validate -v <path-to-edn-file>

The -v (verbose) flag provides detailed error information.

2. Interpret Results

Exit codes:

  • 0 - Validation successful (all checks pass)
  • 1 - Validation failed (schema or semantic errors)
  • 2 - File error (not found, parse error, etc.)

3. Validation Checks Performed

Schema Validation (Malli):

  • Node structure: :id, :type, :statement, :content-hash, :dependencies, :scope, :justification, :status, :taint, :depth, :parent, :display-order, :provenance
  • Valid node types: :assumption, :local-assume, :local-discharge, :definition, :claim, :lemma-ref, :external-ref, :qed
  • Valid justifications: 23 allowed keywords (:modus-ponens, :universal-intro, etc.)
  • Valid statuses: :proposed, :verified, :admitted, :rejected
  • Valid taint values: :clean, :tainted, :self-admitted
  • Symbol, external-ref, lemma, and metadata structure

Semantic Validation:

  • Referential integrity: All :dependencies reference existing nodes; all :lemma-id and :external-id references exist
  • Acyclicity: No cycles in the dependency graph
  • Scope validity: :scope entries are valid (undischarged ancestor :local-assume nodes)
  • Taint correctness: :taint values match computed values based on :status and dependencies

Output Format

On success:

OK: All validations passed

On failure, report:

VALIDATION FAILED: <filename>
================================

ERRORS:
- [<error-type>] <detailed message>
- ...

SUMMARY:
- Schema errors: <n>
- Semantic errors: <n>

RECOMMENDATIONS:
- <specific fixes for each error>

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 13 tokens per session scan A bdf8af917f38

Subscribe to this mod's changes

validate-graph is a command published in the GitHub repository tobiasosborne/alethfeld (144 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 697 once invoked, about $0.0001 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.