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 criterium/opencode-lab --skill memory-systemgit clone --depth 1 https://github.com/criterium/opencode-labWrote 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/criterium/opencode-lab/memory-system)<a href="https://agentmods.dev/skills/criterium/opencode-lab/memory-system"><img src="https://agentmods.dev/badge/skills/criterium/opencode-lab/memory-system/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/criterium/opencode-lab/memory-system"><img src="https://agentmods.dev/badge/skills/criterium/opencode-lab/memory-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 99 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 254 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 179 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 202 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 210 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 371 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 271 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.05504 |
| Opus 5.5 | $0.00000 | $0.02202 |
| Sonnet 5.5 | $0.00000 | $0.01101 |
| Haiku 4.5 | $0.00000 | $0.00550 |
Grade A, and why
memory-system 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 1mo 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System — editing rules
Loaded by custom.md upon receiving >> or <<. Single file per scope (memory.md)
that accumulates relevant project information.
In effect until the skill is loaded again. Apply the certainty rule without asking.
Terminology
- memory-system or m-s: memory files of the scope managed by this skill:
memory.md,memory/*.md,todo.md,checkpoint.md.sessions.mdis an optional historical record, not included.
Source of truth
The definitive source of truth is codebase + database. Memory describes, code executes. Any claim in memory about files, symbols, data structures or schemas must be verifiable against the code on disk. If memory and code disagree, code prevails. The model decides how and what to verify based on context and available tools (grep, glob, DFM parsing).
Division principle
memory.mdself-contained for initial orientation: critical rules, context, map. An agent without context must be able to start with<< ./and understand the project.memory/*.mdis on-demand deepening: implementation detail, specific references. Loaded only when the task requires them.- The index of
memory.mdmust include a column indicating for which type of task to load each file frommemory/. todo.md: pending tasks.<<shows it.>> <scope> checkreports status. Written via>> <scope> todo <content>or manually.
Writing principle
Any content under this skill must prioritize precision and effectiveness over verbosity or human-oriented explanations. Prefer: imperative over descriptive, concrete examples over generalities, direct references over introductions. No politeness, narrative or justifications. Compactness is a consequence, not a goal — do not sacrifice clarity for brevity.
Verification criteria:
- (a) Unambiguous. In what is stated, not in what is omitted. Uncertainty is declared, not hidden in vague wording.
- (b) Action, not description. For instructions and prompts: what to do, not what each thing is. Conditions, preconditions and guard clauses are part of the instruction.
- (c) Action precedes reason. For instructions and prompts: the what before the why.
- (d) No fossils. Do not include implementation dates, versions ("since X"), or counts that expire ("17 forms"). Current state describes how things are, not when they changed. The temporal delta belongs to git / sessions.md.
- (e) Compact by default. One idea = one paragraph. Tables for relatable data. If something is explained in one line, do not expand it to three.
- (f) Relevant. Only what an agent would lose without help deserves memory. Do not store: obvious code structure, standard framework patterns, available official documentation, or conventions inferable from project context.
- (g) Fresh and actionable. Information must be the latest available. If it describes code, verify the code still exists (files, functions, routes). If it describes a decision, it must be the current one. An entry unverified since creation is a review candidate. Prioritize: design decisions, undocumented workarounds, execution orders, non-obvious setup, context inferred from multiple sources.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 374 lines · 0 tokens per session scan A e753ac8cbbe0
memory-system is a skill published in the GitHub repository criterium/opencode-lab (45 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,504 tokens. 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 skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…