Install
$ agentstack add skill-digital-stoic-org-agent-skills-save-work ✓ 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.
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
Save Session
Menu-driven session save for non-CLI interfaces (Cowork desktop, Telegram, CC CLI). Same CONTEXT file format as retrospect:save-context / retrospect:load-context — files are interchangeable.
Target: 1200-1500 tokens MAX for CONTEXT file
Phase 1: Detect Current Project (parallel)
Glob: CONTEXT-*-llm.md (current dir, exclude done/)
Read: CLAUDE.md (first 5 lines, for project name from H1 — required)
Identify:
- Project name (from CLAUDE.md H1 heading — all CLAUDE.md files must have
# Project Nameas first line) - Existing CONTEXT streams (filenames → stream names)
If no CLAUDE.md found in current dir or parents → warn: "⚠️ No project context detected. Use /switch first to select a project."
Before Phase 2: run quality self-check from reference.md — if session is trivial, confirm with user before proceeding.
⚠️ AskUserQuestion Guard
After EVERY AskUserQuestion call, check if answers are empty/blank. If empty: output "⚠️ Questions didn't display (known bug).", present options as numbered text list, WAIT for user reply.
Phase 2: Ask Save Type + Stream (single menu when possible)
0-1 existing streams → merge type + stream into 1 question:
💾 Save {stream-name} as:
1. 🔄 Checkpoint — I'll continue later
2. ✅ Done — this work is finished
3. 🅿️ Parking — switching to something else
Which one? (1/2/3)
Where {stream-name} = existing stream name, or auto-generated from project + conversation topic if no streams exist.
2+ existing streams → 2 questions. First ask stream:
📝 Save to which session?
1. 📍 {stream-1} (existing)
2. 📍 {stream-2} (existing)
3. ✨ New session
Which one?
Then ask save type (same 3-choice menu as above).
New stream confirmation (when auto-generated or user picks "New"):
📝 Stream name: {suggested-name}
OK? (yes / type a different name)
Mapping:
- 1 → status:
building - 2 → status:
done - 3 → status:
parked
Stream naming: pattern ^[a-zA-Z0-9_-]{1,50}$. Reserved: default → CONTEXT-llm.md, baseline.
Phase 3: Drift Check (ref/ vs wip/)
Skip if no ref or wip folder exists in the current project.
Folder aliases: ref/ or reference/ (whichever exists). wip/ or work-in-progress/ (whichever exists). Use the actual folder name found for all subsequent operations.
Quick scan — must complete in unexpected:` for future reference.
Phase 4: Synthesize & Write
From conversation (last 15-20 messages), synthesize:
- Next — 3 tasks (IMPORTANT: use heading "Next" — Claude Code compaction grep-matches
next/todo/pendingkeywords for survival priority) - Session — progression, decisions, thinking, unexpected (780 tokens max)
- Hot Files — max 10 discussed/edited
- Focus & Goal — 1-2 sentence focus + goal
Write CONTEXT file using template from reference.md.
Filename: default → CONTEXT-llm.md, otherwise CONTEXT-{stream}-llm.md
Phase 5: Auto-Archive
If status is done or parked:
Bash: mkdir -p done && mv CONTEXT-{stream}-llm.md done/
Exceptions — do NOT move:
CONTEXT-llm.md(default stream)CONTEXT-baseline-llm.md- If user explicitly says "keep here"
Phase 6: Confirm
💾 Saved: CONTEXT-{stream}-llm.md
📊 Status: {emoji} {status}
📍 Focus: {1-line focus}
📋 Next tasks:
- {task 1}
- {task 2}
- {task 3}
If archived: 📦 Archived to done/ (status: {status})
Rules
- Never ask for stream name as free text first — always offer existing streams or auto-suggest
- 3 choices max per menu — don't overwhelm
- Auto-detect over ask — project name, stream name, status should be inferred when possible
- Same CONTEXT file format as retrospect:save-context — files must be readable by both /load-work and retrospect:load-context
- Client-agnostic output — works in terminal, Cowork, Telegram
- Token budget — CONTEXT file stays under 1500 tokens
- No shell scripts — pure tool calls only (Glob, Read, Write, Edit). Only Bash for
mkdir -p done && mv
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: digital-stoic-org
- Source: digital-stoic-org/agent-skills
- 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.