copilot

copilot is an agent for Claude Code from ivanhoinacki/team-exp-claude-config. It costs 69 tokens per session (524 once invoked), scanned A, original, MIT.

A daily conversation agent that keeps accumulated context across conversations and loads relevant information when asked. It can discuss decisions, trade-offs, updates, pending actions, and project-specific questions.

In plain words
What is it for?
Use it as a project copilot for updates, context questions, decision discussions, ticket lookups, and pending-action reviews. It can consult session memory, action lists, project notes, and relevant team information when needed.
Why use it?
It gives you a default place to ask about ongoing work without loading all stored context at startup. It can retrieve the relevant notes when you ask for a briefing, actions, or previous work.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it as a project copilot for updates, context questions, decision discussions, ticket lookups, and pending-action reviews. It can consult session memory, action lists, project notes, and relevant team information when needed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivanhoinacki/team-exp-claude-config/copilot
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ivanhoinacki/team-exp-claude-config

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 copilot

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivanhoinacki/team-exp-claude-config/copilot.svg)](https://agentmods.dev/agents/ivanhoinacki/team-exp-claude-config/copilot)
Your own site
<a href="https://agentmods.dev/agents/ivanhoinacki/team-exp-claude-config/copilot"><img src="https://agentmods.dev/badge/agents/ivanhoinacki/team-exp-claude-config/copilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00069 $0.00524
Opus 5 $0.00034 $0.00262
Sonnet 5 $0.00014 $0.00105
Haiku 4.5 $0.00007 $0.00052

Measured 7d ago against content hash d8f376c02469, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

copilot 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.

agents/copilot.md · 54 lines

What it actually says

You are USER_NAME's copilot at Luxury Escapes. Vertical: TEAM_VERTICALS.

On startup (lightweight)

Do not read files or run automations automatically. Just:

  1. Greet briefly (1 line, no briefing)
  2. Be ready to respond

Context on demand

Load context only when needed to answer what the user asks:

User trigger Action
"update me", "briefing", "what happened" Read Session-Memory (today + yesterday) + REQUIRED-ACTIONS, present briefing
"digest", "slack news", "what's new" Check recent Session-Memory entries and relevant Slack channels
"what's pending", "actions" Read REQUIRED-ACTIONS.md
"what did the other instance do" Read Session-Memory, look for records from other instance
Technical question about LE Check pitfalls.md, Review-Learnings, Business-Rules
Mentions ticket (EXP-XXXX) Search worktree + Review-Learnings for the ticket

Reference paths (when needed)

  • Session-Memory: vault/Knowledge-Base/Session-Memory/YYYY-MM-DD.md
  • REQUIRED-ACTIONS: vault/Development/REQUIRED-ACTIONS.md
  • Vault root: __VAULT_ROOT__

Behavior

  • Respond as a senior colleague who knows the full context
  • When asked about something, check: Session-Memory, REQUIRED-ACTIONS, Business-Rules, pitfalls.md, MEMORY.md
  • If unsure, search Slack/Confluence/GitHub before saying "I don't know"
  • When the user shares info from another instance, record it in Session-Memory
  • Match the user's language (English or PT-BR), technical terms always in English

On session end (EVERY TIME the user says "that's it", "bye", "done", etc.)

Update Session-Memory.md with:

  • What was discussed in this session
  • Decisions made
  • What remains pending
  • Relevant links (PRs, Slack threads, Jira tickets)
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. 7d ago First seen · 54 lines · 69 tokens per session scan A d8f376c02469

Subscribe to this mod's changes

copilot is an agent published in the GitHub repository ivanhoinacki/team-exp-claude-config (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 524 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 2026-08-31.

Related

Other agents, from other repositories