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.
git clone --depth 1 https://github.com/ivanhoinacki/team-exp-claude-configWrote 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/agents/ivanhoinacki/team-exp-claude-config/copilot)<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>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 | $0.00069 | $0.00524 |
| Opus 5 | $0.00034 | $0.00262 |
| Sonnet 5 | $0.00014 | $0.00105 |
| Haiku 4.5 | $0.00007 | $0.00052 |
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.
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:
- Greet briefly (1 line, no briefing)
- 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)
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 · 54 lines · 69 tokens per session scan A d8f376c02469
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.
Other agents, from other repositories
worker-publisher
Execute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.
tl-archivist
Specialist subagent for thoughtline memory hygiene. Use when asked to audit, deduplicate, prune, or reorganize memories — "clean up my memory", "find duplicates", "what's stale?", "auditá la base", "qué memorias podemos archivar?". Read-mostly, never deletes without explicit user confirmation.
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.