Session Handoff
Capture a durable, privacy-safe handoff at the end of a coding or research session. Use when Codex must preserve repository state, decisions, validation results, blockers, and exact next steps so the next human or AI agent can resume without rediscovering context.
Install
$ agentstack add skill-bglglzd-agent-workflows-session-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 Used
- ✓ 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-bglglzd-agent-workflows-session-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
Session Handoff
Preserve the state needed to resume work accurately. Do not treat a chat summary as durable project memory.
Workflow
- Inspect the workspace before writing: git status, current branch, latest commit, relevant changed files, project docs, and safe command output from this session.
- Reuse the project's existing memory or handoff convention. If none exists, create
docs/ai/SESSION_CONTEXT.mdas the current source of truth anddocs/ai/SESSION_LOG.mdas an append-only dated record. - Update the current-context file with:
- goal and current repository state;
- completed changes with relevant file paths;
- decisions and rationale;
- system, deployment, PR, issue, or external-service context that is safe to record;
- commands run and validation results;
- risks, blockers, and unknowns;
- ordered next actions and a precise resume checklist.
- Append a concise dated log entry with the completed work, validation, and next action.
- Finish by naming the updated files, the highest-priority next action, and the remaining unknowns.
Guardrails
- Never copy tokens, passwords, private URLs, connection strings,
.envvalues, or customer data into project memory. - Do not modify application code, infrastructure, or external systems merely to create a handoff.
- Preserve history instead of overwriting useful records.
- Mark unverified details as Unknown. Do not infer them from incomplete context.
- Include exact file paths, branch or PR identifiers, and commands wherever they make resumption faster.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bglglzd
- Source: bglglzd/agent-workflows
- License: MIT
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.