Borrowing it
Nothing to install: this file belongs to parcadei/ContinuousClaudeV4.7. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/parcadei/ContinuousClaudeV4.7/main/.claude/skills/resume-handoff/SKILL.mdgit clone --depth 1 https://github.com/parcadei/ContinuousClaudeV4.7Wrote 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.
[](https://agentmods.dev/skills/parcadei/continuousclaudev4.7/resume-handoff)<a href="https://agentmods.dev/skills/parcadei/continuousclaudev4.7/resume-handoff"><img src="https://agentmods.dev/badge/skills/parcadei/continuousclaudev4.7/resume-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.
<a href="https://agentmods.dev/skills/parcadei/continuousclaudev4.7/resume-handoff"><img src="https://agentmods.dev/badge/skills/parcadei/continuousclaudev4.7/resume-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00667 |
| Opus 5 | $0.00005 | $0.00333 |
| Sonnet 5 | $0.00002 | $0.00133 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
resume-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 10d 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.
What it actually says
Resume work from handoff through interactive analysis. Handoffs contain critical context, learnings, next steps from previous sessions requiring full understanding before continuation.
Parameter Handling: If handoff path provided, immediately read document and linked research/plans under thoughts/shared/plans or thoughts/shared/research — no sub-agents for critical files. If ticket number (ENG-XXXX) provided, list thoughts/shared/handoffs/ENG-XXXX/ contents. Zero files or missing directory: "Can't find handoff, please provide path." One file: proceed. Multiple files: use most recent by YYYY-MM-DD_HH-MM timestamp. No parameters: respond with "I'll help resume from handoff. Which would you like? Tip: /resume_handoff path or /resume_handoff ENG-XXXX"
Next Session Prompt Priority: After reading handoff, check for next_session_prompt: field. If exists, present directly: "Previous session left prompt: > {contents} Shall I proceed or adjust approach?" If user approves, execute as-is using rest of handoff for context. Skip analysis steps — they're for handoffs lacking direct prompts.
Full Analysis (when no next_session_prompt): Read handoff completely without limit/offset. Spawn focused research tasks verifying current state — gather artifact context from feature docs, implementation plans, research documents mentioned. Wait for ALL sub-tasks before proceeding. Read critical files from learnings and recent changes sections.
Present Synthesis: "Analyzed handoff from [date]. Current situation: Original Tasks: [task]: [handoff status] → [current verification]. Key Learnings Validated: [learning with file:line] - [still valid/changed]. Recent Changes Status: [change] - [verified/missing/modified]. Artifacts Reviewed: [doc]: [takeaway]. Recommended Next Actions: [logical steps from handoff]. Potential Issues: [conflicts/regressions]. Shall I proceed with [action] or adjust?"
Resume Autonomous Session: After presenting synthesis and getting confirmation, check for an existing /autonomous session in continuum/autonomous/. If one exists with pending milestones, resume it — the handoff provides updated context and mental model, /autonomous drives execution. If no autonomous session exists, offer to start one using the handoff's next: steps and next_session_prompt: as the task specification.
Validation Approach: Be thorough — read entire handoff, verify ALL mentioned changes exist, check for regressions/conflicts, read referenced artifacts. Be interactive — present findings before starting, get buy-in on approach, allow course corrections, adapt based on current vs handoff state. Leverage handoff wisdom — pay attention to learnings section, apply documented patterns, avoid mentioned mistakes, build on discovered solutions.
State Verification: Never assume handoff state matches current. Verify file references exist, check for breaking changes since handoff, confirm patterns still valid. Handle scenarios: clean continuation (proceed with recommendations), diverged codebase (reconcile differences, adapt plan), incomplete work (complete unfinished first), stale handoff (re-evaluate strategy given major 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.
- 10d ago First seen · 20 lines · 11 tokens per session scan A 1092092a1d96
resume-handoff is a skill published in the GitHub repository parcadei/ContinuousClaudeV4.7 (48 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 667 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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.…
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…
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.
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.