handoff-resume

handoff-resume is a skill for Claude Code, Codex from pedroiff0/awesome-skills. It costs 95 tokens per session (1,097 once invoked), scanned A, original, MIT.

A guide for continuing unfinished coding work across sessions by reading a HANDOFF.md file and checking the actual Git working tree.

In plain words
What is it for?
It is for resuming branches with open pull requests, reconciling notes with current files, and reviewing repository rules before making the next change.
Why use it?
It helps preserve decisions and distinguish completed, uncommitted, and still-pending work when a repository is picked up later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit It is for resuming branches with open pull requests, reconciling notes with current files, and reviewing repository rules before making the next change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedroiff0/awesome-skills/handoff-resume
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.

Any agent
npx skills add pedroiff0/awesome-skills --skill handoff-resume
Clone the repo
git clone --depth 1 https://github.com/pedroiff0/awesome-skills

Made for: Claude Code, Codex.

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-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/handoff-resume/github.svg)](https://agentmods.dev/skills/pedroiff0/awesome-skills/handoff-resume)
Your own site
<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/handoff-resume"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/handoff-resume/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-resume

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/handoff-resume"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/handoff-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00095 $0.01097
Opus 5 $0.00048 $0.00549
Sonnet 5 $0.00019 $0.00219
Haiku 4.5 $0.00010 $0.00110

Measured 8d ago against content hash e5aebca0c246, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

handoff-resume scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

with curl, grepping for the new element ids / markup:
skills/software-development/handoff-resume/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Resume

Resume multi-session coding work without losing context. The repo carries a HANDOFF.md (continuity doc) and/or a dirty working tree with in-progress edits on a branch that tracks an open PR.

When to use

  • User says "retomar de HANDOFF.md", "continue from ", "voltar ao trabalho em ".
  • git status shows modified/untracked files and a branch tracking a remote PR.
  • You need to know what's done vs in-progress vs pending before touching anything.

Steps

  1. Read HANDOFF.md (or the named file) fully. It records branch, last commit, PR number, committed vs uncommitted files, decisions/why, and pending tasks. This is the map, not the ground truth.
  2. Reconcile with reality. Run git status + git diff --stat (and git diff on suspect files). HANDOFF can be stale — the tree is the truth. A "clean" HANDOFF often hides many already-modified files.
  3. Read the repo's rule files: AGENTS.md, CLAUDE.md, DESIGN.md. These carry architectural rules and design-system gates you must not violate.
  4. Find the gap. What the user now wants vs what's already in the tree. Disambiguate repo jargon from the code, not from the word alone — e.g. a "módulo de velocidade" in a finance app with only Finanças/Investimentos/ Veículos means the Veículos module (km, odômetro). Read the code to confirm before acting.
  5. Make the change. Reuse existing helpers/patterns instead of inventing: if the frontend already has SVG chart helpers (barrasAgrupadas, rosca, legenda), call them for the new graph rather than pulling in a chart lib.
  6. Verify (see Verification path below). Keep any design-system lint at 0 errors.
  7. Update HANDOFF.md with the new state, then commit on the EXISTING branch and push (updates the open PR automatically). Do NOT open a new branch or a new PR unless explicitly told.

Verification path (when you can't trust a visual screenshot)

This environment's browser_vision often returns a blank viewport for server-rendered pages, while the accessibility tree is reliable. Don't block on the blank screenshot — verify with:

  • browser_snapshot (full) — confirms rendered elements, heading levels, and <image> roles carrying native <title> tooltips (proof the SVG chart drew).
  • browser_console — must show 0 JS errors after navigation.
  • Live server check: for Dockerized apps, rebuild and hit the real endpoint with curl, grepping for the new element ids / markup: docker compose -p fa build app app-demo && docker compose -p fa up -d app app-demo (optionally reseed: docker compose -p fa exec -T app-demo node scripts/seed-demo.js) then curl -s -b cookies <url> | grep 'id="chart-..."'.
  • Treat browser_vision as a bonus only. A blank return is a tooling quirk, not evidence the page is broken.

Read the full file on GitHub · 74 lines

Files

What ships with it

1 file 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. 8d ago First seen · 74 lines · 95 tokens per session scan A e5aebca0c246

Subscribe to this mod's changes

handoff-resume is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 1,097 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.