handoff-session-loop

A skill that runs selected Handoff development tasks through a developer, tester, and reviewer cycle. Handoff is the project's task-management system for coordinating this work.

In plain words
What is it for?
Use it when explicitly running a Handoff task loop in Codex for work that needs implementation, testing, and review within the current project.
Why use it?
It adds a controlled review loop around ready tasks and avoids changing task state incorrectly when the required Handoff connection or permissions are unavailable.

Skill for Claude CodeCodex

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/alphaelements/handoff-mcp/handoff-session-loop
Any agent
npx skills add alphaelements/handoff-mcp --skill handoff-session-loop
Clone the repo
git clone --depth 1 https://github.com/alphaelements/handoff-mcp

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,236 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 $0.00051 $0.01236
Opus 5 $0.00026 $0.00618
Sonnet 5 $0.00010 $0.00247
Haiku 4.5 $0.00005 $0.00124

Measured 2d ago against content hash 504a8da5908a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

handoff-session-loop 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.

plugins/handoff-task-loop-codex/skills/handoff-session-loop/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Session Loop

Use this skill only after an explicit user request. It is a Codex-native orchestrator: do not invoke Claude Code commands, Claude workflows, or files from plugin-task-loop/.

Read references/manager.md before selecting work. Before each delegation, read the matching role template in references/ and replace every <placeholder> with the task-specific facts. The templates define the required inputs and report format; the Manager remains accountable for all Handoff state changes.

Prerequisites and safety

  1. Confirm that the Handoff MCP tools are available. If they are not, explain that the project must first configure Handoff MCP; do not emulate its task state by editing .handoff/ files.
  2. In non-interactive codex exec, confirm that Handoff write calls are explicitly permitted before selecting work. Set mcp_servers.handoff.default_tools_approval_mode = "auto" for the controlled invocation, or use the interactive CLI. If Handoff write calls are cancelled, do not delegate work or leave tasks in_progress; report the configuration blocker instead.
  3. Work only in the current project. Never push, publish, deploy, run a migration, or perform a destructive operation without the user's explicit approval.
  4. The root agent is the Manager. It retains responsibility for task state and final verification; child agents must not mark a task done merely because their local work appears complete.
  5. Treat every child-agent failure, timeout, or missing report as a failed gate, never as a pass.

Start and select work

  1. Call handoff_load_context for the current project. If it asks for an active session, immediately call handoff_save_context with session_status: "active", inherited context, a concrete next action, and a checklist item.
  2. Call handoff_list_tasks. Select only tasks that are todo, have no unfinished dependencies, and have a clear, independently writable file scope. Inspect each candidate with handoff_get_task before choosing it.
  3. If scope, acceptance criteria, required tooling, or file ownership is unclear, leave the task todo or set it to review and ask the user for direction. Do not invent requirements.
  4. Form small batches. Concurrent developer work is permitted only when the selected tasks do not share files or generated outputs. Keep one available collaboration slot for the Manager; otherwise run work sequentially.
  5. Before delegating a leaf task, update it to in_progress with handoff_update_task. Supply a positive schedule.estimate_hours when required by Handoff.

Read the full file on GitHub · 110 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 110 lines · 51 tokens per session scan A 504a8da5908a

Subscribe to this mod's changes

handoff-session-loop is a skill published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,236 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens