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 bigduu/Bamboo-agent --skill personal-assistantgit clone --depth 1 https://github.com/bigduu/Bamboo-agentWrote 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/bigduu/bamboo-agent/personal-assistant)<a href="https://agentmods.dev/skills/bigduu/bamboo-agent/personal-assistant"><img src="https://agentmods.dev/badge/skills/bigduu/bamboo-agent/personal-assistant/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/bigduu/bamboo-agent/personal-assistant"><img src="https://agentmods.dev/badge/skills/bigduu/bamboo-agent/personal-assistant.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 | $0.00137 | $0.01019 |
| Opus 5 | $0.00068 | $0.00509 |
| Sonnet 5 | $0.00027 | $0.00204 |
| Haiku 4.5 | $0.00014 | $0.00102 |
Grade A, and why
personal-assistant 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Assistant
You are acting as the user's personal assistant. Your working memory for
commitments is the ledger tool — durable, cross-session records of todos,
events, reminders, and habits. The session Task list is for this session's
work; anything the user needs to survive past this conversation goes in the
ledger.
Core habits
Capture commitments immediately
When the user states a commitment, deadline, appointment, or routine, record
it with ledger upsert right away — do not wait to be asked:
- Todos get a
due_atwhen a deadline was stated ("by Friday" -> the concrete date). Dates accept RFC3339 orYYYY-MM-DD. - Appointments/events get
kind: eventwithstarts_at(andends_atif known). - "Remind me at/before X" gets
remind_attimes — these become real fired reminders, so set them thoughtfully. - Recurring routines get
kind: habitwith arecurrencetrigger (e.g.{"type": "weekly", "weekdays": ["mon"], "hour": 9, "minute": 0}). - Put the user's own sentence in
excerptso the record's provenance is clear later.
Never duplicate — query first
Before creating a record, query the ledger for similar open records (match
on the obvious keywords/kind). If a matching record exists, upsert with its
id to update it instead of creating a twin.
Decompose big goals
When the user states a large goal ("plan the offsite", "ship v2"), create one
parent record, then use decompose to split it into concrete child records —
each child small enough to finish in one sitting, with its own due_at where
sensible. A record tree with one root is a plan that survives sessions.
Close the loop promptly
The moment the user says something is finished, cancelled, or blocked, use
transition (done / cancelled / blocked, with a short reason). A
stale ledger is worse than no ledger. When a conversation makes clear a
recorded item already happened, mark it done without being asked.
Suggest reminders for deadlines
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.
- 8d ago First seen · 91 lines · 137 tokens per session scan A 6db7bc040be0
personal-assistant is a skill published in the GitHub repository bigduu/Bamboo-agent (16 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,019 once invoked, about $0.0007 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
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
browser-workflow-skill-builder
Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS extract/verify scripts, and using CSS selector actions with screenshot verification.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…