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 agentmods add commands/zach-source/mcp-rust-proxy/mcp-proxy-end-sessiongit clone --depth 1 https://github.com/zach-source/mcp-rust-proxyWhat 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 | $0.00010 | $0.00195 |
| Opus 5 | $0.00005 | $0.00097 |
| Sonnet 5 | $0.00002 | $0.00039 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
mcp-proxy-end-session 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 3d 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
End the current tracking session and generate session analytics.
Arguments:
- $1: Session score from -1.0 to 1.0 (optional)
- $2: Session feedback comment (optional)
Example: /mcp-proxy:end-session /mcp-proxy:end-session 0.8 "Productive session, solved the problem"
Instructions for Claude:
- Read current session_id from /tmp/mcp-proxy-current-session
- Call mcp__proxy__tracing__end_session tool
- If session score provided ($1), also call mcp__proxy__tracing__submit_feedback for each response in session
- Display session summary:
- Total responses in session
- Contexts used
- Average quality score
- Suggest improvements for next session
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.
- 3d ago First seen · 25 lines · 10 tokens per session scan A 966330e88aec
mcp-proxy-end-session is a command published in the GitHub repository zach-source/mcp-rust-proxy (5 stars, last pushed 10mo ago), licensed MIT. It adds 10 tokens to every session and 195 once invoked, about $0.0001 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 commands, from other repositories
load
Session lifecycle management with Serena MCP integration for project context loading.
save
Session lifecycle management with Serena MCP integration for session context persistence.
VibeGuard: Learn
Dual-mode learning: (A) Extract guard rules from errors (B) Extract reusable skills from discoveries. Automatic mode routing.
AI: Handoff
Generate a HANDOFF.md snapshot of session state for cross-session continuity.
INFO
Каждый новый терминал = новая сессия = пустой контекст. Агент не знает по какому проекту работаем, какой стек, какие серверы, где деплой, какие активные задачи. Пользователь вынужден на каждом старте перечислять одно и то же — теряется время и мысль.
avatar-orchestrator
Use the preference model to triage several blockers/decisions when is unreachable. It may execute only work that is already authorized, reversible, local, and low-impact. Read the avatar files in and follow START.md.