handoff-guard
Standing instruction for long-running tasks that need token-efficient continuity across context pressure, usage/rate limits, user token budgets, or mid-task…
Skill by MethosPi
Chalk Labs
Need help deploying handoff-guard?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/methospi-handoff-guard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/handoff-guard
What's inside
- Skill name
handoff-guard- Description
- Standing instruction for long-running tasks that need token-efficient continuity across context pressure, usage/rate limits, user token budgets, or mid-task stops.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
While this skill is active: 1. Keep working normally, but save a handoff whenever the task should move cleanly to another agent, another model, or another phase such as planning, implementation, or review. 2. Save proactively when visible warnings show context pressure, usage/rate limits, or a user-provided token budget threshold. As a default, offer a handoff around 10% remaining and save immediately around 5% remaining. Do not wait for the agent to hit a hard stop. 3. Execute the CLI yourself. Do not ask the user to copy-paste commands. 4. Run `pnpm dlx delta-torch init` once per project if `.handoff/` is missing. 5. Save with `pnpm dlx delta-torch save --reason <reason>` and use short reasons such as `plan-complete`, `ready-for-implementation`, `ready-for-review`, or `context-limit`. 6. After saving, tell the user to continue the task in another agent using the short task number, for example: `Continue task #3 in Codex`. 7. Never include secrets, `.env` contents, tokens, or private keys in the checkpoint. If the user asks to continue a suspended task by number, name, or `latest`, run `pnpm dlx delta-torch resume <selector>` yourself and continue from the saved prompt.
From MethosPi/delta-torch, MIT.
More from MethosPi/delta-torch
- 0.411score
handoff-save
MethosPi
Saves a compact handoff checkpoint into .handoff/ before the current session loses useful context or hits usage, rate, or token-budget pressure.
SkillDFreshness: DClaude Code +9 - 0.409score
delta-torch
MethosPi
Use DeltaTorch to preserve, resume, and hand off long-running coding tasks between Codex, Claude Code, Copilot, and local agents.
SkillDFreshness: DClaude Code +9 - 0.404score
handoff-resume
MethosPi
Loads the latest or named handoff checkpoint and continues the task from a short task number, reason, or full id.
SkillDFreshness: DClaude Code +9 - 0.404score
handoff-status
MethosPi
Shows recent handoff checkpoints and the active project handoff state.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 26, 2026 (6 months ago)
- Last release
- Apr 26, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MethosPi/delta-torch
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MethosPi
- 0.411score
handoff-save
MethosPi
Saves a compact handoff checkpoint into .handoff/ before the current session loses useful context or hits usage, rate, or token-budget pressure.
SkillDFreshness: DClaude Code +9 - 0.409score
delta-torch
MethosPi
Use DeltaTorch to preserve, resume, and hand off long-running coding tasks between Codex, Claude Code, Copilot, and local agents.
SkillDFreshness: DClaude Code +9 - 0.404score
handoff-resume
MethosPi
Loads the latest or named handoff checkpoint and continues the task from a short task number, reason, or full id.
SkillDFreshness: DClaude Code +9 - 0.404score
handoff-status
MethosPi
Shows recent handoff checkpoints and the active project handoff state.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get handoff-guard running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
handoff-guard skill. Agent Mart. https://agentmart.dev/skills/methospi-handoff-guard (last updated 2026-10-24)