agentmods.dev

mtk-agent-toolkit: Skill for Claude Code

.claude/skills/handoff/SKILL.md

handoff is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 39 tokens per session (755 once invoked), scanned A, original, MIT.

A session handoff tool that records the current coding work in a short recovery note. It captures items such as the branch, uncommitted changes, recent commits, decisions, blockers, and important files.

In plain words
What is it for?
Use it to prepare a new session or teammate to continue in-progress work with the relevant state and next steps.
Why use it?
It prevents unfinished work from having to be rediscovered after a long session, context limit, teammate handoff, or branch change.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit 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 mtk-agent-toolkit configures →

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mtk plugin — 33 skills, 7 agents, 6 hooks shipped together

not rated 9repo changed 8d ago A scan SkillSpector: warn 39 tokens original MIT
View source ↗ moberghr/mtk-agent-toolkit moberghr.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/handoff/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 33 skills, 7 agents, 6 hooks.

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/moberghr/mtk-agent-toolkit/handoff/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/handoff)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/handoff"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/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/moberghr/mtk-agent-toolkit/handoff"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 135
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00039 $0.00755
Opus 5.5 $0.00016 $0.00302
Sonnet 5.5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 8d ago against content hash bbdb8b4d3484, 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 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.

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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

Overview

A pointer for the next reader, not a transcript. Compaction, the session-start re-injection of tasks/todo.md and recent handoffs, and the workflow artifact already carry your own session forward; write a handoff when a teammate (or a fresh session tomorrow) must pick up unfinished work.

When To Use

  • Handing work to a teammate, or ending a session with non-trivial uncommitted work
  • The engineer asks to "save state" or "hand off" — not when everything is committed with a clear message

Workflow

Resolve the helpers once (project-local first, then the plugin root):

res() { [ -n "${MTK_HELPER_ROOT:-}" ] && echo "$MTK_HELPER_ROOT/scripts/$1" || ([ -f "scripts/$1" ] && echo "scripts/$1" || echo "${CLAUDE_PLUGIN_ROOT}/scripts/$1"); }
WFA="$(res workflow-artifact.sh)"; HS="$(res handoff-state.sh)"

Resume mode first. If the request is to continue / resume / pick up, or /mtk handoff arrives while bash "$HS" list --open --branch "$(git branch --show-current)" shows an open note and the engineer did not ask to save state: do not write a note (three sessions regenerated one instead of resuming).

  1. bash "$WFA" resume "$(bash "$HS" field <note> workflow)" — online, so PR drift is checked. Read the note.
  2. bash "$HS" accept <note> (expire for an obsolete note). If a helper is missing or exits non-zero, say the note's state was not updated.
  3. Continue from next_command; the user's latest message wins over the note.

Write mode. The script renders the whole note (frontmatter, git facts, PRs/CI, units, traps); you supply only the next step, decisions and open questions.

  1. Active workflow: bash "$WFA" checkpoint "$MTK_WF_UUID" --next "<what the next session does first>" --decision "<decision — one-line reason>"… [--needs-user "<question> | default: <default>"]. No active workflow: MTK_WF_UUID=$(bash "$WFA" init TASK --goal "<goal>"), then checkpoint.
  2. Exit 3 means --next names a finished unit: fix the text and re-run (nothing was written).
  3. Notes are git-ignored via docs/handoffs/.gitignore, created by the script; they expire after 14 days.
  4. Update the workflow's Claude Artifact per .claude/references/artifact-publishing.md (no-op when unavailable or MTK_ARTIFACT_PUBLISH=0; disk first).
  5. Tell the engineer the note path and any artifact URL: "after /clear, type anything — the next session is offered this checkpoint".

Read the full file on GitHub · 46 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. 8d ago Changed · -13 lines bbdb8b4d3484
  2. 13d ago Changed · +15 lines 65e90ae8d521
  3. 16d ago Changed · -108 lines · -3 tokens per session f643594a92f3
  4. 1mo ago Changed 1d8533c746e9
  5. 2mo ago First seen · 152 lines · 42 tokens per session scan A 87b162c10f9b

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 755 once invoked, about $0.0002 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 2026-08-31.

Memory and context
Related

Other skills, from other repositories

knowledge-ingest

Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…

openclaw/openclaw · 80 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 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