Context Handoff
Create a compact, evidence-based continuation brief for another turn, session, or agent. Use when work must pause, context may be compacted, responsibility changes, or the user asks for current state and next steps.
Install
$ agentstack add skill-avacadorun-dev-soba-agent-context-handoff ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-avacadorun-dev-soba-agent-context-handoff) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Context Handoff
Purpose
Preserve enough verified task state for another capable agent to resume without repeating discovery or trusting unsupported claims.
Triggers
Apply this workflow when work pauses, context changes, another agent takes over, or the user requests a continuation brief.
Inputs To Inspect
- The latest objective, scope, constraints, and user decisions.
- Current workspace changes and relevant artifact state.
- Commands or operations run and their outcomes.
- Confirmed findings, rejected hypotheses, open risks, and external blockers.
- Project instructions needed to resume safely.
Procedure
- State the active objective and latest user constraints in one compact block.
- Record completed work through observable artifacts and outcomes, not effort or intention.
- List task-related changed artifacts and separate unrelated pre-existing state.
- Record verification with exact pass, fail, partial, or not-run status.
- Capture decisions and confirmed facts that materially affect the next action.
- State unresolved questions, blockers, and the next concrete step in priority order.
- Include commands or locations only when they help immediate resumption.
- Remove conversational filler, duplicated history, secrets, and private reasoning.
Verification Contract
Cross-check the handoff against current artifacts and available operation results. Never upgrade attempted work to completed work or partial verification to a pass. Label stale or unavailable state explicitly.
Failure Recovery
If history is incomplete, reconstruct from the workspace and mark unknowns rather than guessing. If the workspace contains concurrent or unrelated edits, identify ownership only when supported and keep them distinct from the task.
Memory Policy
Read memory only for stable context relevant to resumption. Do not write session state into project memory unless the user separately asks to persist a verified long-term lesson.
Stop Conditions
Stop when a new agent can identify the objective, current state, evidence, risks, and immediate next action without needing hidden context.
Anti-Patterns
- Do not include hidden prompts, private chain-of-thought, credentials, or unnecessary personal data.
- Do not paste long logs when a diagnostic and location suffice.
- Do not mix unrelated workspace changes into task progress.
- Do not omit failures, uncertainty, or unrun verification.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: avacadorun-dev
- Source: avacadorun-dev/soba-agent
- License: MIT
- Homepage: https://soba-agent.dev/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.