Softcover: Skill for Claude Code

.claude/skills/handoff/SKILL.md

handoff is a skill for Claude Code from CinqueIzumi/Softcover. It costs 30 tokens per session (1,019 once invoked), scanned A, original, MIT.

A session handoff helper that records the current work, next action, open questions, verification, and uncommitted changes in a project tracker before asking about committing.

In plain words
What is it for?
Closing a work session and updating the active task's Now section for another session.
Why use it?
It lets a later coding session resume from a concise status record instead of reconstructing what happened.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is CinqueIzumi/Softcover's own configuration. It tells Claude Code how to work on Softcover itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Softcover configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CinqueIzumi/Softcover. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CinqueIzumi/Softcover/main/.claude/skills/handoff/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/CinqueIzumi/Softcover

Made for: Claude Code.

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/cinqueizumi/softcover/handoff/github.svg)](https://agentmods.dev/skills/cinqueizumi/softcover/handoff)
Your own site
<a href="https://agentmods.dev/skills/cinqueizumi/softcover/handoff"><img src="https://agentmods.dev/badge/skills/cinqueizumi/softcover/handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/cinqueizumi/softcover/handoff"><img src="https://agentmods.dev/badge/skills/cinqueizumi/softcover/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.01019
Opus 5.5 $0.00012 $0.00408
Sonnet 5.5 $0.00006 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured 12d ago against content hash cebf184f2002, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 12d 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.

.claude/skills/handoff/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

Close out this session so a fresh one can pick up from the tracker alone. The next session starts from the ## Now block of the tracker listed in docs/working/ACTIVE.md, so that block must carry everything it needs.

Procedure

  1. Resolve the tracker. Read docs/working/ACTIVE.md (one repo-relative path per line). If it lists one file, use it. If it lists several and this session touched more than one of them, ask the user which to hand off. If it is missing or empty, tell the user and stop.

  2. Run the close-out gate when this session changed Kotlin (git diff --name-only HEAD plus untracked *.kt):

    • Grep the changed *.kt files for a glommed closer, ^\s*\)\s*\}. Every hit on a multi-line trailing-lambda body is a finding.
    • In changed test files, every @Test function carries // ----- Arrange -----, // ----- Act ----- and // ----- Assert ----- (or the combined // ----- Act & Assert ----- only where the act cannot be separated). A missing marker is a finding.
    • ./gradlew styleCheck must have passed this session, after the last Kotlin edit. If not, run it.

    Any finding or a failed styleCheck means the step is not done: State must not call it done, and the findings go under Next. Write the gate results under Verification.

  3. Rewrite its ## Now block (everything from ## Now up to the next ## heading) to this shape, at most 40 lines:

    ## Now
    
    - **State:** what is done, in one or two sentences. Name finished steps/sections, not the journey.
    - **Next:** the exact next action, with repo-relative file references (the step file and section,
      e.g. `steps/02-gradle-and-read-guards.md` § 3). One item, not a list of options.
    - **Open questions:** anything waiting on the user, or "none".
    - **Verification:** the last gate that ran and its result (e.g. "`./gradlew styleCheck` passed"), or
      "not run" with the reason.
    - **Uncommitted:** a summary of `git status --short` (step 5).
    

Read the full file on GitHub · 69 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. 12d ago Changed · +23 lines cebf184f2002
  2. 1mo ago First seen · 46 lines · 30 tokens per session scan A 969d013fcf31

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository CinqueIzumi/Softcover (16 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,019 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-26.