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 richfrem/agent-plugins-skills --skill os-lab-memorygit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/os-lab-memory)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-lab-memory"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-memory/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/richfrem/agent-plugins-skills/os-lab-memory"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-memory.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 | $0.00073 | $0.00538 |
| Opus 5.5 | $0.00029 | $0.00215 |
| Sonnet 5.5 | $0.00015 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
os-lab-memory 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 yesterday.
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
Session Memory Manager (os-lab-memory)
Manages the three tiers of agent memory in an Agentic OS environment: Auto-memory (MEMORY.md), Long-term facts (context/memory.md), and Session logs (context/memory/YYYY-MM-DD.md).
Contents
Critical Constraints
- Conflict Resolution: Never overwrite
context/memory.mdwith conflicting facts without prompt and resolution. - Enduring Facts Only: Do not promote ephemeral error messages, test noise, or single-use bash commands.
- Lock Release: Always release
memorylock upon completion or error recovery.
Quick start
Check current memory file size and status:
wc -c context/memory.md
Workflow
- Acquire Lock: Acquire
memorylock viakernel.py:python3 scripts/kernel.py acquire_lock memory - Record Session Log: Write dated session summary to
context/memory/YYYY-MM-DD.md. - Promote Long-Term Facts: Append vetted architectural decisions to
context/memory.mdwith conflict checks. - Enforce Size Limits: If
context/memory.mdexceeds 50,000 bytes, prune or archive oldest entries tocontext/memory/archive/. - Release Lock:
python3 scripts/kernel.py release_lock memory
Verification
Confirm memory update is persisted and lock is released:
python3 scripts/kernel.py state_read
References
- detailed-reference.md — Tiered memory architectures and promotion protocols.
- acceptance-criteria.md — Acceptance criteria for memory promotions.
- fallback-tree.md — Recovery procedures when locks fail or collisions occur.
What ships with it
11 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.
- evals/evals.json 1.7 KB
- evals/results.tsv 60 B
- references/acceptance-criteria.md 56 B
- references/architecture.md 35 B
- references/architecture/claude-md-hierarchy.md 58 B
- references/architecture/context-folder-patterns.md 62 B
- references/detailed-reference.md 55 B
- references/fallback-tree.md 50 B
- references/memory-promotion-guide.md 45 B
- references/memory/post_run_survey.md 48 B
- scripts/kernel.py 26 B runs code
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.
- yesterday First seen · 65 lines · 73 tokens per session scan A ce8e9f65227a
os-lab-memory is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 538 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 2026-10-16.
Other skills, from other repositories
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
compact-now
Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…
session-handoff
Makes sessions durable across /clear, machine reboots, and IDE switches. SessionStart catchup pulls scratch + last MemPalace recall + planning files into context. Stop promotion writes a handoff note and runs memory-keeper. Manual /mddesign:handoff re-runs either at any time.
chief-of-staff
Skill "chief-of-staff" from aimerdoux/wavex-os, covering 🧭 chief of staff, 🧠 your identity & memory, 🎯 your core mission, 💭 your communication style and 🚨 critical rules you must follow.
chief-of-staff
Personal Chief of Staff system for ADHD-ish operators. Vault-based, loop-driven, nervous-system-aware. Built and lived-in across daily sessions on real consulting, content, and long-running personal work.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.