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.specify)<a href="https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.specify"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.specify/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.specify"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.specify.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 | $0.00033 | $0.00556 |
| Opus 5 | $0.00016 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
speckit.memory-md.specify 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specify With Memory
Before writing or revising the feature spec, resolve configuration. If .specify/extensions/memory-md/config.yml exists, read it for memory_root, specs_root, feature_memory_filename, memory_synthesis_filename, and optimizer. Otherwise use defaults: memory_root: docs/memory, specs_root: specs, feature_memory_filename: memory.md, memory_synthesis_filename: memory-synthesis.md.
- Prepare Context: Run
/speckit.memory-md.prepare-context --feature specs/<feature>or callspeckit_memory_refresh_cache(scope="all")(to sync backup.mdfiles to SQLite if empty) and thenspeckit_memory_synthesize(feature="specs/<feature>"). - Read Synthesis: Read
specs/<feature>/memory-synthesis.mdto identify constraints and decisions relevant to this feature. - Targeted Search: If the synthesis is insufficient, call
speckit_memory_searchto query the SQLite cache. Do NOT read.mdmemory files directly. The SQLite cache is the single source of truth.
Retrieval Order
- Read config.
- Read the Governance Layer (
.specify/memory/) constitution, standards, or principles first. - Call
speckit_memory_searchor use MCP tools for any durable memory queries. Do NOT read{memory_root}/INDEX.mdor other memory.mdfiles directly. - Read existing
{specs_root}/<feature>/{memory_synthesis_filename}when present. - Read any nearby feature memory from related unfinished work when clearly relevant.
Do not load all durable memory files. Rely on the MCP tools which respect configured retrieval budgets.
After Reading
- Extract only the constraints, reused decisions, bug patterns, and architecture boundaries relevant to this feature.
- Write or refresh
{specs_root}/<feature>/{feature_memory_filename}with feature-local notes and open questions. - Write or refresh
{specs_root}/<feature>/{memory_synthesis_filename}with a compact summary for planning and implementation, withinretrieval.max_synthesis_wordsdefaulting to 900 words. - Call out conflicts between the requested feature and existing durable memory.
- Separate durable project memory from transient feature context.
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 · 35 lines · 33 tokens per session scan A ab994f57c7e4
speckit.memory-md.specify is a command published in the GitHub repository DyanGalih/spec-kit-memory-hub (15 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 556 once invoked, about $0.0002 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.