handoff

handoff is a skill for Claude Code, Codex from Gnayj/claude-code-sop. It costs 99 tokens per session (1,587 once invoked), scanned A, original, MIT.

A session-start summary of a project’s active work, boundaries, decisions, review state, and next step.

In plain words
What is it for?
Use it when resuming work or switching tasks, especially before implementation or fixes that depend on the project’s current task records.
Why use it?
It gives a new or returning coding agent the essential project context without requiring a full read of every document.

Skill for Claude CodeCodex

Part of the ccsop plugin — 5 skills, 5 commands, 3 agents shipped together

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/gnayj/claude-code-sop/handoff
Any agent
npx skills add Gnayj/claude-code-sop --skill handoff
Clone the repo
git clone --depth 1 https://github.com/Gnayj/claude-code-sop

Made for: Claude Code, Codex.

Or install ccsop, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 3 agents.

Wrote 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.

agentmods badge for handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/gnayj/claude-code-sop/handoff.svg)](https://agentmods.dev/skills/gnayj/claude-code-sop/handoff)
Your own site
<a href="https://agentmods.dev/skills/gnayj/claude-code-sop/handoff"><img src="https://agentmods.dev/badge/skills/gnayj/claude-code-sop/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,587 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 $0.00099 $0.01587
Opus 5 $0.00049 $0.00794
Sonnet 5 $0.00020 $0.00317
Haiku 4.5 $0.00010 $0.00159

Measured 4d ago against content hash 20c66ac32da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

skills/handoff/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff Skill

Emit a structured handoff of the current project for fast alignment at session start or when switching the active task.

Design principles

  1. Always read from the source of truth: every invocation re-reads docs/records/current.md
    • the active task artifacts; this skill caches no state summary, so there is no staleness risk.
  2. Cover the minimal quality gate: the output must include each active task's goal / scope / non-goals / acceptance / review state / collaboration boundary / locked decisions / next step, to prevent scope drift in later implement / fix.
  3. Not a substitute for the source: handoff is a startup summary; before implement / fix you must still read the full task card (this skill is not ground truth).
  4. Do not read archive / topic design docs / full SOP / closed-out task cards (unless the user explicitly asks).

Steps (do not skip any)

Step 1 — Read docs/records/current.md

This skill reads current.md's actual section structure (do not assume fixed section numbers). Extract:

  • the current-state section (the top "current state / at a glance" summary).
  • under the pause-points / active-tasks section, every active task sub-section, but skip the closeout/archive index (those are archived tasks, not active).
  • each active task sub-section typically carries: the artifact path, design-pre-review state / verdict, and closeout state.

Step 2 — Extract active task-card / design-doc paths

From the active sub-sections, pull every active artifact path by prefix keyword (language-tolerant), covering two kinds:

Prefix keyword Path Case
task card: / 任务卡: docs/plans/active/<...>.txt multi-round / relay (N≥2 implement card)
design doc: / design 文档: docs/methodology/<...>-design.md or docs/design/<...>/*.md N=1 single-round implement (no implement card; the design doc is the round contract — see claude-code-sop-collaboration.md §4.1)

Read the full file on GitHub · 118 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.

  1. 4d ago First seen · 118 lines · 99 tokens per session scan A 20c66ac32da6

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository Gnayj/claude-code-sop (2 stars, last pushed 23d ago), licensed MIT. It adds 99 tokens to every session and 1,587 once invoked, about $0.0005 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

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens