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.share-lesson)<a href="https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.share-lesson"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.share-lesson/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.share-lesson"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.share-lesson.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 | $0.00020 | $0.00595 |
| Opus 5 | $0.00010 | $0.00298 |
| Sonnet 5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
speckit.memory-md.share-lesson 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 11d 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.
What it actually says
Share Lesson
Promote an approved local lesson (e.g. database optimizations, security constraints, framework-specific gotchas) into the global cross-project shared memory.
This action is automatic based on your confidence score. Evaluate the proposed lesson for sharing. If your confidence is > 50% that it is highly reusable, automatically share it. If your confidence is <= 50%, ignore it. However, you must always allow the user to trigger this manually if they explicitly request it.
Use this when:
- you have successfully implemented a complex feature or fixed a recurring bug
- you have verified and written the lesson into a local memory file (e.g.,
decisions/,bugs/,architecture/) - the lesson has high reuse potential for other projects sharing the same language or framework
Tasks:
-
Identify the local memory entry to promote:
- ID: unique stable identifier (e.g.,
L12,A4) - Title: short descriptive title
- Content: complete markdown body detail (context, decisions, implementation rules)
- Tags: relevant keywords (e.g.
auth,jwt,security) - Language: e.g.,
typescript,php,go - Framework: (optional) e.g.,
nestjs,laravel
- ID: unique stable identifier (e.g.,
-
Step 2A — Write to Local Memory (if not already captured locally): Call
speckit_memory_registerto write the entry to your localdocs/memory/file and sync the local SQLite cache atomically:speckit_memory_register(id="<id>", title="<title>", tags="<tags>", file="<source_file>", projectRoot="<absolute_path_to_project>", content="<full markdown entry>")Step 2B — Promote to Global Shared Memory: Once captured locally, promote the lesson to the global cross-project cache using the MCP tool:
MCP (Preferred):
speckit_memory_share_lesson(id="<id>", title="<title>", content="<full content>", language="<lang>", framework="<fw>", tags=["<tag1>", "<tag2>"])ℹ️ Step 2A and 2B are separate operations. Step 2A writes to your local
docs/memory/and local SQLite. Step 2B writes to the global~/.spec-kit/shared-memory.sqlite. Both steps are needed for a fully published lesson. -
Confirm that the lesson is successfully published to the global SQLite database. Reassure the user that the project's real directory path is fully anonymized (never shared or exported; represented globally only by a cryptographic hash).
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.
- 11d ago First seen · 44 lines · 20 tokens per session scan A c6954a05d225
speckit.memory-md.share-lesson is a command published in the GitHub repository DyanGalih/spec-kit-memory-hub (15 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 595 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.