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 markoblogo/abvx-agent-skills --skill personal-workspace-routergit clone --depth 1 https://github.com/markoblogo/abvx-agent-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/markoblogo/abvx-agent-skills/personal-workspace-router)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/personal-workspace-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/personal-workspace-router/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/markoblogo/abvx-agent-skills/personal-workspace-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/personal-workspace-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00745 |
| Opus 5 | $0.00027 | $0.00373 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
personal-workspace-router 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 2d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Workspace Router
Build a compact local operating layer above project repos. The goal is not one giant memory file; it is routing to the smallest relevant context.
Workspace Shape
WORKSPACE/
├── AGENTS.md
├── MEMORY.md
├── DECISIONS.md
├── ROUTING-LOG.md
└── domains/
└── <domain>/
├── AGENTS.md
└── MEMORY.md
Core Rules
- Root router first:
AGENTS.mdmaps domain signals todomains/<name>/. - On-demand domain context: read only the routed domain's
AGENTS.md; read itsMEMORY.mdonly when durable preferences matter or the user asks about remembered context. - Professional role routing: inside the selected domain, choose one primary role and only the supporting professionals needed for the current deliverable. A role changes stance and context, not authority.
- User-triggered memory: write memory only when the user explicitly says to remember, log, save, note, or not forget something.
- Conflict check: if a requested memory contradicts existing memory, show the conflict and ask how to reconcile it.
- Decision log sparingly: append one-line preference signals to
DECISIONS.mdonly after meaningful forks. - Routing log sparingly: append to
ROUTING-LOG.mdonly after user correction, a new durable signal, or repeated ambiguity.
Domain Creation
When adding a domain:
- Ask a short interview:
- domain name;
- routing signals;
- repo paths or external surfaces;
- default stance and forbidden actions;
- what memory is safe to store.
- Create
domains/<domain>/AGENTS.md. - Create
domains/<domain>/MEMORY.mdwith a user-triggered policy and empty entries. - Add the domain to the root routing map.
- Define initial professional role profiles only for current repeated work; route ambiguous intake through the personal assistant/coordinator.
Guardrails
- Do not ask for confirmation before every routine step; ask only when route, memory, or action risk is real.
- Do not store secrets, credentials, private contacts, raw transcripts, or bulky logs.
- Do not turn every successful route into a routing-log entry.
- Do not let personal workspace rules override repo-local safety, tests, or approval gates.
- Do not treat role routing as durable memory, model selection, tool permission, or external-action approval.
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.
- 2d ago Changed · +4 lines · -5 tokens per session e68fa174d013
- 11d ago First seen · 68 lines · 59 tokens per session scan A e0b7dbe2b55f
personal-workspace-router is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 745 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
debug-memory
Query and manage the executable feedback debug memory.
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
role-skill-boundary-audit
Audit where governance instructions belong (Role.md, skill, global policy, workflow docs, memory, or an agent-boundary change); enforce minimal verbosity in roles and skills. Diagnostic by default.
save-bugfix
After resolving any bug, save what broke, the root cause, and the fix as a CogmemAi memory so the same problem never has to be debugged twice. Use immediately after a bug is fixed, after diagnosing a flaky test, after recovering from a production incident, or after the user says "got it working", "that fixed it"…