Delegate independent tasks to specialized agents working concurrently with isolated context.
/land - End Session
land
End session. Reconciles exploration folders, appends context to CAPCOM, syncs Beads, displays session stats.
SKILL.md
Full skill instructions
/land - End Session
Capture session context in CAPCOM and reconcile any folder states that were missed during the session.
Procedure
Step 0: Reconcile Exploration Folders
Check for folder/state mismatches and fix them:
| If folder in... | But has... | Move to... |
|---|---|---|
exploration/ideas/ | plan.md | exploration/planned/ |
exploration/planned/ | Beads feature exists | mission/staged/ |
mission/staged/ | Beads feature closed | mission/complete/ |
For each mismatch: show user, confirm, then mv the folder.
Step 1: Gather State
git branch --show-current
git status --short
git log -1 --oneline
bd stats
bd list -t feature --status in_progress
From your session memory, note:
- Tasks completed this session
- Bugs fixed this session
- Active feature and its progress (done/total tasks)
Step 2: Append to CAPCOM
Get next session number:
grep -c "^## \[.*\] Session [0-9]" .space-agents/comms/capcom.md 2>/dev/null || echo 0
Add 1 to get the next session number.
Append full session context to .space-agents/comms/capcom.md:
## [YYYY-MM-DD HH:MM] Session {N}
**Branch:** {branch} | **Git:** {clean/uncommitted}
### What Happened
[Narrative of what was worked on. Be specific - file names, function names, what changed and why.]
### Decisions Made
[Architectural decisions, trade-offs chosen, "we decided X because Y". Skip if none.]
### Gotchas
[Things that surprised you, bugs encountered, "watch out for X". Skip if none.]
### In Progress
[If stopped mid-task: what state, next step, files involved. Skip if clean stop.]
### Next Action
[One clear thing to do next session.]
---
Guidelines:
- Be specific ("added JWT refresh in auth/tokens.ts:45" not "updated auth")
- Include file paths where relevant
- Capture reasoning, not just actions
- Skip empty sections
- CAPCOM is append-only
Step 3: Land
Pre-flight:
bd doctor --quiet # Warn on failures, don't block
git status # Review pending changes
Stage and commit:
git add <specific files> # Stage code changes (not -A)
bd sync # Sync beads
git commit -m "feat: <summary from session>" # Meaningful message
git push
Commit message should summarize session work (e.g., "feat: update agent terminology, complete feature 1.2").
Step 4: Display Summary
Query features and show progress:
bd list -t feature
bd list --tree
Output format:
SESSION COMPLETE
────────────────
Tasks completed: {count from session}
Bugs fixed: {count from session}
FEATURES
{for each feature from bd list -t feature}
{status_icon} {feature_title} [{closed_tasks}/{total_tasks}]
{end for}
Context saved to CAPCOM. Run /launch to continue.
Safe travels, Commander.
Status icons: ✓ closed, ◐ in_progress, ○ open, ● blocked
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
