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 agentmods add skills/jarroslav/agentic-os/role-memorynpx skills add Jarroslav/agentic-os --skill role-memorygit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/role-memory)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/role-memory"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/role-memory.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.01825 |
| Opus 5 | $0.00079 | $0.00912 |
| Sonnet 5 | $0.00032 | $0.00365 |
| Haiku 4.5 | $0.00016 | $0.00183 |
Grade A, and why
role-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 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
role-memory
Give the agent a memory that survives context resets. Each role owns a directory of plain markdown you manipulate directly with your file tools. No wrapper binary, no shell-path dependence — the layout is identical on every host.
Two stores, two costs. The daily log is cheap and episodic: one appended line per observation, no promise of lasting value. A curated entry is durable — a fact expected to stay useful for roughly six months — and costs one index slot. Spend the expensive store deliberately.
When to use
- User says "remember this", "log this", or asks "what did you learn yesterday".
- You learn something durable — a preference, a validated correction, a project constraint, a pointer to an external system — that a future session would waste effort rediscovering.
- You are about to act and need to recall what this role already knows.
Role identity
The role is the agent's own name: frontmatter value (e.g. project-manager, python-dev,
scout). Every fact below scopes to <role>; each role gets its own directory. Never read or write
another role's memory.
Layout (fixed contract)
.agents/memory/<role>/ contains:
| Path | What it is |
|---|---|
MEMORY.md |
The curated index — one line per entry. |
<slug>.md |
One curated entry (durable fact/preference/decision/pointer). |
project_briefing.md |
The scout-seeded project entry (stack, conventions, role pitfalls). |
daily/YYYY-MM-DD.md |
One episodic log file per day. |
snapshot.md |
Supervisor-generated digest — you never write this. |
.agents/ is chosen as an IDE-neutral root so the tree is the same across hosts. Create directories
lazily with mkdir -p on first use. You may add role-specific operational files to the directory
(for example a personal-assistant's people-pending.md) as long as the core files above keep their
formats.
Curated entry format
Exactly three frontmatter keys, no extras, one per line — the supervisor's snapshot regenerator parses these:
What ships with it
2 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.
- 4d ago First seen · 179 lines · 159 tokens per session scan A 5afc3fd25c36
role-memory is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 159 tokens to every session and 1,825 once invoked, about $0.0008 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…