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.
npx skills add dizeldz20-ux/agent-shared-memory --skill asm-reviewgit clone --depth 1 https://github.com/dizeldz20-ux/agent-shared-memoryWrote 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/skills/dizeldz20-ux/agent-shared-memory/asm-review)<a href="https://agentmods.dev/skills/dizeldz20-ux/agent-shared-memory/asm-review"><img src="https://agentmods.dev/badge/skills/dizeldz20-ux/agent-shared-memory/asm-review/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/skills/dizeldz20-ux/agent-shared-memory/asm-review"><img src="https://agentmods.dev/badge/skills/dizeldz20-ux/agent-shared-memory/asm-review.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 | $0.00067 | $0.00690 |
| Opus 5.5 | $0.00027 | $0.00276 |
| Sonnet 5.5 | $0.00013 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
asm-review 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 29d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASM review
The janitor (cleanup layer) and the curator (learning layer) write every change through the lifecycle ledger. Classes the owner has not yet trusted wait here as proposals. Nothing is applied without the owner's explicit choice in this conversation.
Steps
- List:
node ~/.asm/jobs/dist/runner/cli.js reviewprints JSON — one entry per class with its mode (proposeorauto) and its items (id, summary, target, evidence, reason). - Show the owner, in the owner's language, one group per class, at most five items per group
(the rest as a count). For each item: what it closes or changes, why, and the evidence id.
Open an evidence record with
mcp__asm__brain_node("memory:<id>")when the owner asks. The curator's classes change text (block.refresh,index.rewrite,memfile.compact,correction.apply): for each such item runnode ~/.asm/jobs/dist/runner/cli.js show <id>and show the lines it removes and adds in every file it touches — anindex.rewritealso moves the old line into the memory file's History.changed_since: truemeans the file changed after the proposal was built; applying it will be deferred. Aquarantinedgroup lists items that failed three times; every run skips them. Name them to the owner; there is nothing to apply. - Ask one question: which items to apply.
- Act on the answer, and only on it:
- apply:
node ~/.asm/jobs/dist/runner/cli.js apply <id …|class:<name>|all> - reject:
node ~/.asm/jobs/dist/runner/cli.js reject <id …|class:<name>|all> - undo an applied operation:
node ~/.asm/jobs/dist/runner/cli.js restore <op-id> "<reason>"
- apply:
- Report one line per class: applied, rejected, deferred.
Rules
- A
deferredresult means a live session changed the file after the proposal was built. Say so; it leaves the queue and the next run rebuilds it on the file as it is now. applyreturnspromoted: the classes this approval moved to automatic. Tell the owner.- A first build of a project's current-state block always waits for the owner, whatever the
trust state. Rejecting a
correction.applycloses the agent's correction request. - Never edit proposal, ledger or trust files by hand.
- A class moves to automatic only through clean approvals on three separate days (a backlog approved in one sitting counts once); restoring an automatic operation moves its class back to proposals.
- Status and the judge gate:
node ~/.asm/jobs/dist/runner/cli.js status.
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.
- 29d ago First seen · 45 lines · 67 tokens per session scan A a7c754b96103
asm-review is a skill published in the GitHub repository dizeldz20-ux/agent-shared-memory (1 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…