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 borisvu/obsidian-vault-cowork-plugins --skill memory-managementgit clone --depth 1 https://github.com/borisvu/obsidian-vault-cowork-pluginsWrote 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/borisvu/obsidian-vault-cowork-plugins/memory-management)<a href="https://agentmods.dev/skills/borisvu/obsidian-vault-cowork-plugins/memory-management"><img src="https://agentmods.dev/badge/skills/borisvu/obsidian-vault-cowork-plugins/memory-management/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/borisvu/obsidian-vault-cowork-plugins/memory-management"><img src="https://agentmods.dev/badge/skills/borisvu/obsidian-vault-cowork-plugins/memory-management.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 | $0.00047 | $0.02182 |
| Opus 5 | $0.00023 | $0.01091 |
| Sonnet 5 | $0.00009 | $0.00436 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
memory-management 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 9d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management (PARA Edition)
Memory makes Claude a workplace collaborator who speaks your internal language.
The Goal
Transform shorthand into understanding:
User: "ask john about the audit issue on project-7292"
↓ Claude decodes
"Ask John Smith (CTO) about the audit operation failure
on PROJECT-7292 (Audit operation ended without results, P1 bug)"
Architecture
CLAUDE.md ← Hot cache (~30 people, common terms, active projects)
PARA/
0 Inbox/ ← Unsorted items (scanned during --comprehensive update)
1 Projects/ ← Active project folders + Jira tickets (assigned to you)
{Project Name}/ ← Subdirectory per project with notes inside
{KEY} - {Summary}/ ← Jira ticket subdirectory (when assigned to you)
2 Areas/
People/ ← Individual people profiles
Partners/ ← Partner company profiles
Customers/ ← Customer company profiles
3 Resources/
Terms/ ← Individual term/acronym files (one per term)
Jira/ ← Jira tickets you're not assigned to (flat files)
Company/ ← Company context, teams, tools, processes
4 Archive/ ← Completed projects (by year)
CLAUDE.md (Hot Cache):
- Top ~30 people you interact with most
- ~30 most common acronyms/terms
- Active projects (5-15)
- Your preferences
- Goal: Cover 90% of daily decoding needs
- All entries point to PARA locations for full detail
PARA folders (Deep Storage):
- Rich detail when needed for execution
- Full profiles, histories, context
- Can grow indefinitely — it's an Obsidian vault
PARA Location Mapping
| What | PARA Location | Filename convention |
|---|---|---|
| Person | PARA/2 Areas/People/{Full Name}.md |
Title case, spaces |
| Partner company | PARA/2 Areas/Partners/{Company Name}.md |
Title case |
| Customer company | PARA/2 Areas/Customers/{Company Name}.md |
Title case |
| Active project | PARA/1 Projects/{Project Name}/ |
Subdirectory, Title case |
| Jira ticket (yours) | PARA/1 Projects/{KEY} - {Summary}/{KEY} - {Summary}.md |
Subdirectory with descriptive name |
| Jira ticket (other) | PARA/3 Resources/Jira/{KEY} - {Summary}.md |
Flat file with descriptive name |
| Term / acronym | PARA/3 Resources/Terms/{Term}.md |
One file per term |
| Company context | PARA/3 Resources/Company/ |
By topic |
| Archived project | PARA/4 Archive/{YYYY}/{Project Name}/ |
By year, subdirectory |
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.
- 9d ago First seen · 237 lines · 47 tokens per session scan A 31978dcce32d
memory-management is a skill published in the GitHub repository borisvu/obsidian-vault-cowork-plugins (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,182 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
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…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.