session-continuity
/session-continuity
Preserves durable session context, handoffs, and next-step clarity across interruptions. Use this skill when pausing work, resuming a thread, or writing handoff notes so another agent or human can continue. Do not use when/for choosing investigation mode (use investigation-modes) or completing a branch (use branch-completion).
- Author
- jagreehal ↗
- Repository
- jagreehal-claude-skills ↗
- Licence
- MIT
- Last repository change
- 30.07.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.07.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Preserves durable session context, handoffs, and next-step clarity across interruptions. Use this skill when pausing work, resuming a thread, or writing handoff notes so another agent or human can continue. Do not use when/for choosing investigation mode (use investigation-modes) or completing a branch (use branch-completion).
Original author description
Preserves durable session context, handoffs, and next-step clarity across interruptions. Use this skill when pausing work, resuming a thread, or writing handoff notes so another agent or human can continue. Do not use when/for choosing investigation mode (use investigation-modes) or completing a branch (use branch-completion).
How it works
- Critical rules
- Workflow
- Resources
- Validation
- Constraints
SKILL.md preview
--- name: session-continuity description: >- Preserves durable session context, handoffs, and next-step clarity across interruptions. Use this skill when pausing work, resuming a thread, or writing handoff notes so another agent or human can continue. Do not use when/for choosing investigation mode (use investigation-modes) or completing a branch (use branch-completion). version: 2.2.0 --- # Session Continuity ## Critical rules - State lives in project `.claude/` files (`tasks.md`, `requirements.md`, `session.md`), not conversation memory. - EVERY message must start with the current state prefix. - Never re-derive progress by investigating the codebase — read `session.md`. - Never auto-advance tasks; never commit for the user; never use TodoWrite. - VERIFY before COMPLETE; mark `[x]` only after user yes in AWAITING_COMMIT. - Before operating or setting up, read [references/state-machine.md](references/state-machine.md) and [references/setup-and-antipatterns.md](references/setup-and-antipatterns.md). ## Workflow 1. On "continue": enter `CHECK_STATUS` — read only `session.md`, route by Status. 2. `WORKING`: implement current task only; update `session.md` at triggers. 3. `VERIFY`: run all requirements verification commands; show output; fail → WORKING. 4. `COMPLETE` → CHECK_STATUS → `AWAITING_COMMIT` (ask permission, STOP). 5. On yes: `MARK_COMPLETE` then CHECK_STATUS for next task. 6. On "create a plan" / "setup tasks": create the three files per setup reference. ## Resources - [references/state-machine.md](references/state-machine.md) — states, transitions, file roles. Read every session. - [references/setup-and-antipatterns.md](references/setup-and-antipatterns.md) — file templates, anti-patterns, path fixes. Read on setup or resume failures. ## Validation - [ ] Every message has state prefix - [ ] Three `.claude/` files exist at project root - [ ] CHECK_STATUS only reads session.md - [ ] VERIFY ran all commands with verbatim output - [ ] No `[x]` without user approval; no TodoWrite; no agent commits ## Constraints - Not for single self-contained one-session changes. - Related: `implementation-planning`, `verification-before-completion`, `tdd-workflow`, `investigation-modes`, `create-tasks`.
Files in this package (3)
- SKILL.md 2 KB
- references/setup-and-antipatterns.md 1 KB
- references/state-machine.md 2 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · jagreehal/jagreehal-claude-skills | 100 | MIT |
| devpilotX/ai-skill-ai | 100 | MIT |
| joogy06/agent-foundry | 100 | MIT |
| ericwang200608-beep/LANYANT-Skills | 85 | MIT |
Database snapshot: 13.11.2026 · package version 47a2ddbe1926 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100session-handoff
Package current session context so another agent can continue without starting cold. Use when the user says "hand this off", "continue in a new session", "save session state", or context limit is approaching. - 90handoff
Write a handoff document so another agent or a fresh session can continue this work. Use for "handoff", "hand this off", "write a handoff", "continue this in a new session" or "pass this to another agent". For deciding whether to compact or clear, use session-budget. - 86handoff
Write or update a HANDOFF.md so a fresh agent can continue this work. Use when the user says "handoff", "compact this", "context is full", or "/clear and continue". - 100compaction-continuity-check
Use when an agent must save a session summary under a stable key so it can resume after context compaction or in a new session. - 82handoff
Summarize the current conversation into a file so another session (or agent) can continue the work with little context. Use when the chat got long, a topic closed, or the person says "handoff", "let's move to a new session" or "save the state so I can continue later". - 100writing-handoffs
Use when the user asks for a handoff prompt, a continuation prompt, or a prompt to continue work in a fresh context window — often phrased as 'give me a handoff prompt', 'I'll clear context', 'so I can continue in a new session'. Also use when wrapping up a session on a…