hades-validate-memory

A command that checks authored Asphodel memory documents for quoted C# file paths that no longer exist in the project graph.

In plain words
What is it for?
Use it to validate memory files and report missing C# paths grouped by the documents that mention them.
Why use it?
It finds broken script-path references in project memory, helping identify one specific kind of documentation drift.

Command

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/thearcforge/hades/validate-memory
Clone the repo
git clone --depth 1 https://github.com/TheArcForge/Hades
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 140 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 $0.00016 $0.00140
Opus 5 $0.00008 $0.00070
Sonnet 5 $0.00003 $0.00028
Haiku 4.5 $0.00002 $0.00014

Measured 2d ago against content hash 796cbd481282, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hades-validate-memory 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 2d 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.

ClaudeCodePlugin/commands/validate-memory.md · 13 lines

What it actually says

Validate memory against the live project graph:

  1. Call validate_memory to check every authored memory document for backtick-quoted .cs paths that no longer exist in the graph.
  2. Report results grouped by document: which document references which missing path.
  3. If results were truncated, say so and suggest a higher limit.

This only catches broken script-path references — not stale prose, outdated decisions, or any other kind of drift. If there are no results, say memory has no dangling .cs references, not that everything in it was confirmed accurate.

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. 2d ago First seen · 13 lines · 16 tokens per session scan A 796cbd481282

Subscribe to this mod's changes

hades-validate-memory is a command published in the GitHub repository TheArcForge/Hades (27 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 140 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.