agentmods.dev

create

create is a command for coding agents from TheMrGU/Ai-Agent-Context-Passoff. It costs 17 tokens per session (349 once invoked), scanned A, original, MIT.

A command for creating a structured handoff from one AI coding session to another. The handoff records the current state, decisions, questions, next steps, and relevant files.

In plain words
What is it for?
Use it to summarize ongoing work, preserve project decisions, identify open questions, and return a handoff ID for the next agent.
Why use it?
It prevents important context from being lost when work moves to another session or agent.

Command

0 4mo ago A scan 17 tokens original MIT
View the source file TheMrGU/Ai-Agent-Context-Passoff
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.

agentmods
npx agentmods add commands/themrgu/ai-agent-context-passoff/create
Clone the repo
git clone --depth 1 https://github.com/TheMrGU/Ai-Agent-Context-Passoff
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00349
Opus 5 $0.00009 $0.00175
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash 21dd29248d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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 2d 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.

commands/codex/commands/create.md · 54 lines

What it actually says

Passoff Create

Create a clean baton-pass handoff using the configured passoff_* MCP tools.

Preflight

  1. Confirm the passoff MCP tools are available in this session.
  2. Inspect the current conversation and working context before writing the handoff.
  3. If there is not enough meaningful context yet, stop and say so rather than creating a low-value handoff.

Plan

  1. Summarize the current state from the active session.
  2. Capture key decisions and rationale.
  3. List open questions and immediate next steps.
  4. Call passoff_create with a terse structured markdown body.

Commands

Call the passoff_create MCP tool with:

  • title: short and action-oriented
  • content: structured markdown with these sections in order:
    • Current State
    • Decisions Made
    • Open Questions
    • Next Steps
    • Relevant Files
  • from_model: the current model id if known
  • project: only if the project identity is clear

Be terse but specific. Include concrete file paths where useful.

Verification

  1. Confirm the tool call succeeded.
  2. Verify a handoff id was returned.
  3. If the call fails, report the failure plainly.

Summary

  • Report the handoff title
  • Report the returned handoff id
  • Report the project scope if available

Next Steps

  • Tell the user another AI can resume from the returned id.
  • Suggest /passoff:load in Codex or the equivalent load flow in another MCP client.
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. 2d ago First seen · 54 lines · 17 tokens per session scan A 21dd29248d87

Subscribe to this mod's changes

create is a command published in the GitHub repository TheMrGU/Ai-Agent-Context-Passoff (0 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 349 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.

Building agentsai-agentsclaude-codecodexcontext-handoffcursordeveloper-tools
Related

Other commands, from other repositories

everme-help

Print a concise EverMe plugin status + reference card.

EverMind-AI/EverMe · 11 tokens

release

Walk the llmwiki release process step by step.

Pratiyush/llm-wiki · 0 tokens

add-agent

引导新增一个 Agent 适配器。用法 /add-agent.

shirenchuang/agentbro · 19 tokens

migrate

Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.

chohra-med/expo_boilerplate · 0 tokens

lians-recall

Recall current (non-stale) facts from Lians memory, optionally as-of a past date.

Lians-ai/Lians · 19 tokens

t800-onboard

Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.

Khar-AG/t-800-agent · 0 tokens