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 ntaffzii/Skill-Agents --skill personal-agent-workflowgit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/personal-agent-workflow)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/personal-agent-workflow"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/personal-agent-workflow.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 5.1 | $0.00075 | $0.00466 |
| Opus 5 | $0.00037 | $0.00233 |
| Sonnet 5 | $0.00015 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
personal-agent-workflow 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 7d 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.
What it actually says
Personal Agent Workflow
Use this skill to make personal context useful without overreaching into private systems.
Operating Rules
- Treat Obsidian/local Markdown and explicit user-provided files as the safest source.
- Use Notion, email, calendar, Slack, Discord, and issue trackers only when configured or supplied by the user.
- Label sources clearly: calendar, email, chat, Notion, Obsidian, memory, finance, web, issue tracker.
- Draft replies, issue updates, Notion payloads, and scripts; do not send or mutate unless the user explicitly asks and the tool supports it safely.
- Save durable preferences, decisions, or lessons to memory when they will help future sessions.
Workflow
-
Scope
- Confirm date/timezone only when ambiguous.
- Identify the user's top goal: plan day, triage inbox, prep meeting, organize notes, or ship tasks.
-
Gather
- Calendar: summarize events and draft meeting prep.
- Email/chat: summarize messages and extract action items.
- Notion/Obsidian: read only relevant notes or pages.
- Memory/RAG: search prior decisions before creating new assumptions.
- Finance: include only when the user asks for markets/watchlists.
-
Decide
- Split work into now, today, later, waiting, and delegated.
- Convert unclear requests into issue drafts or Obsidian tasks.
- Keep personal and public/shareable content separate.
-
Produce
- Provide a concise daily plan or briefing.
- Include draft replies or issue updates in clearly marked sections.
- Offer Notion/Obsidian payloads as plans unless asked to apply them.
Output Shape
For daily planning, end with:
- Today
- Meetings
- Inbox/chat actions
- Notes to save
- Drafts
- Waiting on
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.
- 7d ago First seen · 52 lines · 75 tokens per session scan A 32f0ce90a035
personal-agent-workflow is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 466 once invoked, about $0.0004 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
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).
context-compactor
9-section context compression with analysis scratchpad. Adapted from Claude Code's /compact system (2026-03-31).
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).
trade-journal-analyzer
Unified post-trade analytics: journal pattern extraction + drawdown classification. Absorbs: drawdown-classifier.
Deep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.
academic-delivery
8-step pipeline for academic deliverables — essays, reports, analysis, capstones. Encodes the full intake-to-delivery workflow with automatic red-team triggering.