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.
git clone --depth 1 https://github.com/DyanGalih/spec-kit-memory-hubWrote 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.
[](https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.audit)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 configuredretrieval.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).
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.
- 9d ago First seen · 80 lines · 13 tokens per session scan A 610290dd513a
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.
Other commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-req
Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.
wiki-init
Initialize a new LLM Wiki in the current directory. Creates the full directory structure, config, and template files.
wiki-run
Run the full wiki cycle: discover → ingest → lint. Optionally schedule for auto-updates.