What is source-command-handoff?

A handoff workflow that creates one standard document describing work done in the current session and checks that document afterward.

It is for handing a task from one model to Claude, Gemini, or Codex, including the task summary, current state, next step, workspace, and handoff identifier.

It helps another AI model or session continue work without reconstructing the task from the entire conversation.

source-command-handoff — Skill by baek-labs

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 skills/baek-labs/hames/source-command-handoff

Any agent

npx skills add baek-labs/hames --skill source-command-handoff

Clone the repo

git clone --depth 1 https://github.com/baek-labs/hames

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 609 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.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.00609
Opus 5	$0.00011	$0.00304
Sonnet 5	$0.00004	$0.00122
Haiku 4.5	$0.00002	$0.00061

Measured 2d ago against content hash fc937c0978ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-command-handoff 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.

.codex/skills/source-command-handoff/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-handoff

Use this skill when the user asks to run the migrated source command handoff.

Command Template

/handoff

Usage: /handoff <target_model>

Examples:

/handoff gemini
/handoff codex
/handoff claude

Flow

Step 1 — Confirm target model

Read the user-provided argument and extract the target model (claude, gemini, or codex).
If no target model is given, ask which model should receive the handoff.

Step 2 — Summarize the current session From the active conversation and working context, prepare:

task_summary
current_state
next_step
source_model
source_workspace
handoff_id in the format HAMES-{YYYYMMDD}-{KEYWORD} or SESSION-{YYYY-MM-DD}-{LETTER}

source_workspace must be the real workspace where the work happened. Do not use AI_COMM as the source workspace.

Step 3 — Create the handoff file

powershell -NoProfile -ExecutionPolicy Bypass -File arsenal/create_handoff.ps1 `
  -HandoffId "<handoff_id>" `
  -TargetModel "<target_model>" `
  -SourceModel "<source_model>" `
  -SourceWorkspace "<source_workspace>" `
  -TaskSummary "<task_summary>" `
  -CurrentState "<current_state>" `
  -NextStep "<next_step>"

create_handoff.ps1 builds the handoff document directly from these arguments. Do not depend on .hames_context.json.

Step 4 — Refresh target bootstrap only if needed

For gemini:

powershell -NoProfile -ExecutionPolicy Bypass -File arsenal/start_hames_gemini.ps1 `
  -Task "<task_summary>" `
  -TargetPath "<source_workspace>" `
  -Handoff

For codex:

powershell -NoProfile -ExecutionPolicy Bypass -File arsenal/start_hames_codex.ps1 `
  -Task "<task_summary>" `
  -TargetPath "<source_workspace>" `
  -Handoff

For claude, skip bootstrap generation.

Step 5 — Validate

powershell -NoProfile -ExecutionPolicy Bypass -File arsenal/validate_handoff.ps1 `
  -HandoffFile "ai_comm/_Inbox/Handoff_<handoff_id>.md"

Read the full file on GitHub · 81 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.

2d ago First seen · 81 lines · 22 tokens per session scan A fc937c0978ff

Subscribe to this mod's changes

source-command-handoff is a skill published in the GitHub repository baek-labs/hames (5 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 609 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.

Writing and docs agent-orchestration claude-code codex gemini-cli harness prompt-engineering

source-command-handoff

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

source-command-handoff

Command Template

/handoff

Flow

What this file has done since we first saw it

Other skills, from other repositories

代码审查员

release-gate-loop

fresh-eyes-loop

sofagent-fde

sofagent-audit

sofagent