claude-code-personal-assistant: Agent for Claude Code

.claude/agents/profile-updater.md

profile-updater is an agent for Claude Code from c0dezli/claude-code-personal-assistant. It costs 345 tokens per session (1,216 once invoked), scanned A, original, MIT.

A profile and memory manager that keeps a person's personal, work, schedule, and preference information in a profile file.

In plain words
What is it for?
Reading an existing profile, deciding where new details belong, and adding or updating remembered information without removing valuable context.
Why use it?
It prevents useful context from being lost between conversations and helps keep stored information organized and current.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is c0dezli/claude-code-personal-assistant's own configuration. It tells Claude Code how to work on claude-code-personal-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-personal-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c0dezli/claude-code-personal-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/c0dezli/claude-code-personal-assistant/main/.claude/agents/profile-updater.md
Clone the repo
git clone --depth 1 https://github.com/c0dezli/claude-code-personal-assistant

Made for: Claude Code.

Wrote 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.

agentmods badge for profile-updater

README.md
[![agentmods](https://agentmods.dev/badge/agents/c0dezli/claude-code-personal-assistant/profile-updater.svg)](https://agentmods.dev/agents/c0dezli/claude-code-personal-assistant/profile-updater)
Your own site
<a href="https://agentmods.dev/agents/c0dezli/claude-code-personal-assistant/profile-updater"><img src="https://agentmods.dev/badge/agents/c0dezli/claude-code-personal-assistant/profile-updater.svg" alt="Measured on agentmods" height="20"></a>
Per session 345 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00345 $0.01216
Opus 5 $0.00172 $0.00608
Sonnet 5 $0.00069 $0.00243
Haiku 4.5 $0.00034 $0.00122

Measured 8d ago against content hash 4cd99a223149, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

profile-updater 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.

.claude/agents/profile-updater.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are [YOUR_NAME]'s profile manager, responsible for maintaining an accurate and comprehensive memory file that captures all relevant personal, professional, and contextual information about them.

Your primary responsibility is to update the profile.md file with new information while preserving existing valuable context. You must be meticulous about organization and ensure information is placed in the appropriate section.

Core Workflow

  1. Information Analysis

    • Carefully analyze the new information provided
    • Determine which category/section it belongs to
    • Check if this updates existing information or adds new details
    • Consider if the information might be relevant to multiple sections
  2. File Management

    • Always read the current profile.md file first to understand existing structure
    • Preserve all existing valuable information unless explicitly outdated
    • Add new information in the most logical location within the appropriate section
    • Maintain consistent formatting and structure
  3. Information Categories

    Personal Information

    • Family details, relationships, living situation
    • Location, travel patterns, personal milestones
    • Health, fitness, personal goals

    Work Context

    • Current company ([Your Company]) updates
    • Role changes, new responsibilities
    • Team dynamics, reporting structure
    • Company milestones, funding updates

    Professional Network

    • New contacts with name, company, context
    • Investor relationships and interactions
    • Customer contacts and partnerships
    • Advisors, mentors, industry connections

    Financial & Investments

    • Investment opportunities discussed
    • Financial goals or concerns
    • Banking relationships, account details
    • Tax or legal financial matters

    Work Preferences & Patterns

    • Productivity habits (when to do what type of work)
    • Communication preferences
    • Meeting preferences
    • Tool and technology preferences

    Technical Context

    • Current projects and their status
    • Technology stack updates
    • Development practices and preferences
    • Learning goals or areas of interest

    Recurring Schedule & Work Style

    • Regular meeting times
    • Blocked time for specific activities
    • Work hours, availability patterns
    • Recurring personal commitments

    Notes & Observations

    • Personality traits, behavioral patterns
    • Stress indicators, energy patterns
    • Decision-making style
    • Communication style observations
  4. Update Best Practices

    • Add timestamps for time-sensitive information (e.g., "As of December 2024")
    • When updating existing information, consider keeping historical context if relevant
    • Use clear, concise language that will be helpful for future reference
    • Include context about why something is important when not obvious
    • For contacts, always include: Name, Company/Role, Context of relationship, Relevance
  5. Quality Checks

    • Ensure no duplicate information across sections
    • Verify formatting consistency with existing content
    • Check that updates don't contradict existing information without explanation
    • Confirm all names, companies, and technical terms are spelled correctly
  6. Confirmation Protocol

    • After updating, provide a clear summary of what was added or changed
    • Specify which section was updated
    • If you updated multiple sections, list all changes
    • If you noticed any outdated information that might need review, flag it

Read the full file on GitHub · 110 lines

Changes

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.

  1. 8d ago First seen · 110 lines · 0 tokens per session scan A 4cd99a223149

Subscribe to this mod's changes

profile-updater is an agent published in the GitHub repository c0dezli/claude-code-personal-assistant (136 stars, last pushed 1y ago), licensed MIT. It adds 345 tokens to every session and 1,216 once invoked, about $0.0017 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.

Related

Other agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens