speckit.memory-md.audit

speckit.memory-md.audit is a command for Claude Code from DyanGalih/spec-kit-memory-hub. It costs 13 tokens per session (1,119 once invoked), scanned A, original, MIT.

A read-only review command for a project's saved memory, including its database index and Markdown backups. It checks whether memory is synchronized, current, consistent, and useful to later work.

In plain words
What is it for?
Use it to inspect cache integrity, stale or conflicting memory, noisy entries, accidental data leakage, and synthesis limits before relying on stored project context.
Why use it?
Project memory can contain outdated decisions, contradictions, duplicate information, or broken index entries. This audit helps find those problems without changing the files.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to inspect cache integrity, stale or conflicting memory, noisy entries, accidental data leakage, and synthesis limits before relying on stored project context.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit
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.

Clone the repo
git clone --depth 1 https://github.com/DyanGalih/spec-kit-memory-hub

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 speckit.memory-md.audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit/github.svg)](https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit)
Your own site
<a href="https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit.memory-md.audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit.svg" alt="Reviewed on agentmods" width="80" 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 1,119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01119
Opus 5 $0.00006 $0.00560
Sonnet 5 $0.00003 $0.00224
Haiku 4.5 $0.00001 $0.00112

Measured 9d ago against content hash 610290dd513a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

speckit.memory-md.audit 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 9d 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.

commands/speckit.memory-md.audit.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Memory

You are running a high-integrity audit of the project's durable and feature memory for memory-hub.

Scope note: The tool speckit_memory_audit_cache(scope="memory") validates SQLite cache integrity only (stale hashes, orphaned rows, missing files, synthesis word budget). It does not evaluate content quality. Full content-quality checks (stale decisions, contradictions, leakage, noise) are performed by this AI command only — they require querying the cache or reading the backup markdown files and applying the rubric below.

Goal

Validate the quality, accuracy, and density of memory artifacts. Identify stale, contradictory, or low-signal entries that degrade the project's long-term intelligence.

Audit is intentionally expensive and may read all memory. Normal synthesis must not; it relies on MCP queries. IMPORTANT: You MUST run speckit_memory_audit_cache(scope="memory") first to validate the SQLite cache sync health. If the cache is synced, query the cache for content quality evaluation. If you must read .md backups to evaluate content, read them explicitly using your file-reading tools.

Operating Constraints

  • STRICTLY READ-ONLY: This command is analytical. Do not modify any files.
  • Evidence-Based: Every finding must cite a specific entry or lack thereof.

Detection Scope

Check for:

  • Stale/Obsolete: Decisions or patterns that no longer apply to the current codebase.
  • Contradictions: Memory entries that conflict with the Constitution or other memory files.
  • Noise/Triviality: Routine history, speculative notes, or implementation details that lack durable value.
  • Selection Hygiene: Deprecated or superseded decisions are not selected during synthesis.
  • Leakage: Feature-specific details that belong in {specs_root}/ but have leaked into {memory_root}/.
  • Synthesis Drift: {memory_synthesis_filename} is out of sync with selected memory.
  • Synthesis Budget: {memory_synthesis_filename} exceeds configured retrieval.max_synthesis_words.
  • Formatting Issues: Entries that are too long, vague, or repetitive.
  • Cache Integrity: Missing source files, invalid references, orphaned DB rows, duplicate memory entries, and stale hashes in the local SQLite cache (detected via speckit_memory_audit_cache).

Read the full file on GitHub · 80 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. 9d ago First seen · 80 lines · 13 tokens per session scan A 610290dd513a

Subscribe to this mod's changes

speckit.memory-md.audit is a command published in the GitHub repository DyanGalih/spec-kit-memory-hub (15 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,119 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.