stevengonsalvez/reflect:consolidate
plugins/reflect/skills/consolidate/SKILL.md
Project-level memory consolidation. Merges orphaned worktree memory directories into a single .agents/MEMORY.md for the current project. Deduplicates, sections, and proposes cleanup of orphan dirs. Does NOT index into the global knowledge base — use reflect:ingest for that.
$ install --global
skillsauthnpx skillsauth add stevengonsalvez/agents-in-a-box reflect:consolidateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 19, 2026, 2:32 AM10.5s1 file scanned
SKILL.md
- name:
- reflect:consolidate
- description:
- |
- Does NOT index into the global knowledge base — use reflect:
- ingest for that.
- version:
- 3.0.0
- user-invocable:
- true
- - reflect:
- consolidate
Reflect: Consolidate — Project Memory Cleanup
Merge orphaned worktree memory directories for the current project into a single,
tidy .agents/MEMORY.md. This is a project-level operation — it does not
touch the global knowledge base.
For global indexing (GraphRAG + QMD), use /reflect:ingest after consolidating.
When to Use
- After deleting git worktrees
- When multiple worktree sessions left orphaned memory dirs
- To keep
.agents/MEMORY.mdcurrent and deduped - Before running
/reflect:ingest(consolidate first, then index)
What It Does
- Discovers orphaned worktree memory dirs for the current project
- Reads all MEMORY.md files from those dirs
- Deduplicates entries (fuzzy — same concept = skip)
- Routes skill-worthy content to existing skills
- Writes consolidated
.agents/MEMORY.md(200-line max) - Ensures agent config references it
- Proposes cleanup of orphaned dirs
What It Does NOT Do
- Does NOT index into GraphRAG or QMD (that's
reflect:ingest) - Does NOT scan other tools (Codex, Copilot, Gemini) — project-scoped only
- Does NOT archive originals to
~/.learnings/— that's ingest's job
Pipeline
Step 1: Discover Project Identity
python3 {{HOME_TOOL_DIR}}/skills/reflect/scripts/memory_discovery.py project-id
# -> e.g. "shotclubhouse"
Step 2: Find Orphaned Memory Dirs
python3 {{HOME_TOOL_DIR}}/skills/reflect/scripts/memory_discovery.py discover --provider claude
# Lists all worktree memory dirs for the current repo
# Excludes current session's memory dir
Step 3: Read All MEMORY.md Files
Read from each matched directory. Extract individual entries (sections, bullets, paragraphs).
Step 4: Deduplicate and Categorize
Group by section, remove redundant entries:
- Same concept = skip
- Same error + same solution = skip
- More detailed version = keep the detailed one
Step 5: Route Skill-Worthy Content
Check if entries match existing skill topics (check {{HOME_TOOL_DIR}}/skills/ and
.claude/skills/). Propose adding matching content to those skills.
Step 6: Write .agents/MEMORY.md
Consolidated, deduped, within 200-line limit:
# Project Memory
> Auto-consolidated by /reflect:consolidate. 200-line max.
> Detailed learnings route to skills. Global index via /reflect:ingest.
## Architecture & Patterns
## Build & Deploy
## Gotchas & Workarounds
## Testing
## Environment & Config
Sections are dynamic — empty sections removed, new sections created as needed.
Step 7: Ensure Agent Config Reference
Check if .claude/CLAUDE.md or .claude/AGENTS.md contains @.agents/MEMORY.md.
If not, add it at the top.
Step 8: Propose Orphan Cleanup
Show list of orphaned dirs and ask for confirmation:
# After user approval:
python3 {{HOME_TOOL_DIR}}/skills/reflect/scripts/memory_discovery.py cleanup /tmp/reflect-cleanup-dirs.txt --execute
Step 9: Report
## Consolidation Complete
- **Orphaned dirs processed**: 7
- **Entries consolidated**: 42
- **Duplicates removed**: 15
- **Routed to skills**: 3
- **.agents/MEMORY.md**: 127 lines
- **Dirs cleaned up**: 7
Next: Run `/reflect:ingest` to index into GraphRAG + QMD.
Stats (Quick Check)
Check orphaned memory status without making changes:
python3 {{HOME_TOOL_DIR}}/skills/reflect/scripts/memory_discovery.py stats
# -> Repo: shotclubhouse
# -> Orphaned memory dirs: 7
# -> Total lines across all: 283
Safety
- NEVER auto-apply without user approval
- NEVER delete orphaned dirs without explicit confirmation
- Always show what will be written to
.agents/MEMORY.mdbefore writing - Preserve original structure of existing
.agents/MEMORY.md
Related Skills
stevengonsalvez/reflect:cost
documentation
VerifiedTrustedCommunity
Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Use to answer "what is reflection costing me" for the last day / week.
12SKILL.mdUpdated Jun 2, 2026
stevengonsalvez/ainb-fleet:standup
development
VerifiedTrustedCommunity
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, see which sessions have a peer registered (broker-routable) vs tmux-only, check the `summary` of each session, or pipe the list into jq for filtering. Default output: text table. Pass --format json for LLM consumption.
10SKILL.mdUpdated May 31, 2026
stevengonsalvez/ainb-fleet:sequence
testing
VerifiedTrustedCommunity
Ordered multi-step prompts to fleet targets, ack-gated between steps via JSONL assistant-turn-end detection. Use for cycles like disconnect→reconnect→verify, or any flow where step N+1 requires step N to have completed first. The skill BLOCKS until each target's transcript shows the next assistant turn finishing OR per-step timeout fires (default 300s).
10SKILL.mdUpdated May 31, 2026
stevengonsalvez/ainb-fleet:needs
development
VerifiedTrustedCommunity
Center control panel — enumerate every claude session that is blocked waiting on something: a user answer (AskUserQuestion fired), an API error retry, an idle assistant turn-end with no follow-up, or an explicit WAITING: marker. Returns rich JSON with signal kind + context per session. Use this when you've stepped away from the fleet and want one place to see everything that wants your attention and answer it.
10SKILL.mdUpdated May 31, 2026