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 studiomeyer-io/studiomeyer-marketplace --skill memory-workflowgit clone --depth 1 https://github.com/studiomeyer-io/studiomeyer-marketplaceWrote 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/studiomeyer-io/studiomeyer-marketplace/memory-workflow)<a href="https://agentmods.dev/skills/studiomeyer-io/studiomeyer-marketplace/memory-workflow"><img src="https://agentmods.dev/badge/skills/studiomeyer-io/studiomeyer-marketplace/memory-workflow/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/studiomeyer-io/studiomeyer-marketplace/memory-workflow"><img src="https://agentmods.dev/badge/skills/studiomeyer-io/studiomeyer-marketplace/memory-workflow.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 | $0.00049 | $0.01101 |
| Opus 5 | $0.00024 | $0.00550 |
| Sonnet 5 | $0.00010 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
memory-workflow 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StudioMeyer Memory Workflow
This skill teaches the right tool choice for any memory operation. The Memory server has 56 tools (53 core + 3 UI: nex_graph_view, nex_recall_timeline, nex_session_replay). This is the decision tree for the 10 you will use most.
Core principle
Memory has four types of content:
- Learnings: facts, insights, mistakes, patterns. Append-only with a confidence score. Use
nex_learn. - Decisions: tracked choices with rationale and outcome. Use
nex_decide. - Entities: typed nodes in the Knowledge Graph (people, projects, tools, services). Use
nex_entity_*. - Sessions: conversation containers with start/end markers. Use
nex_session_*.
Search spans all four with nex_search. It is the default for "do we know anything about X?" questions.
Decision tree
User asks about something we might already know
→ nex_search with a natural-language query. Let expand: true (the default) handle synonym expansion. If the query is aggregation-heavy ("how many", "all the", "summarize"), set agentic: true.
User wants to save a fact or insight
→ nex_learn with the right category:
mistake: something that went wrongpattern: recurring techniqueinsight: non-obvious realizationresearch: findings from investigationarchitecture: design decisionworkflow: processsecurity: security-relevant fact
User makes a choice with a reason
→ nex_decide with content, rationale, outcome (if already known). Decisions can be linked with nex_decide follow-ups later.
User mentions a person, project, tool, or service
→ nex_entity_search first to check for duplicates. If not found, nex_entity_create. Then nex_entity_observe to add facts and nex_entity_relate to link it to other entities.
User asks "what's happening" or "what's next"
→ nex_sprint (current tasks) plus nex_proactive (stale items, open decisions, knowledge gaps, pattern clusters, skill fail-rates, unfinished tasks, never-read observations, untagged entries). Start the session with a project: it ranks that working area first and decides where saves without their own project get filed.
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.
- 4d ago Changed 0bdf64aeecac
- 9d ago First seen · 87 lines · 49 tokens per session scan A cd64a2d36a59
memory-workflow is a skill published in the GitHub repository studiomeyer-io/studiomeyer-marketplace (2 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 1,101 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 2026-08-31.
Other skills, from other repositories
memory-protocol
A shared set of rules for using a persistent memory service across coding-agent sessions.
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…