Vault consolidate
Skill pantheon-org/tekhne/skills/agentic-harness/vault-consolidate
Propose or apply consolidation of episodic memories into semantic ones, combining related episodic captures into higher-level semantic summary notes. Use after a long session or when the user asks to clean up, organise, summarise, merge, or declutter memories, or requests memory cleanup or memory management. Always run --propose first so the user can review before --apply commits changes to the vault.From its SKILL.md
npx -y skills add pantheon-org/tekhne --skill vault-consolidateAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 2 commands, including `vault-cli consolidate --propose [--project <id>]` and 1 more.
SKILL.md
2.4 KB, 464 tokens by cl100k_base, as published. Nobody here has run it
vault-consolidate
Cluster related episodic memories and synthesise them into durable semantic notes.
Mindset
Think of --propose as generating a diff and --apply as committing the merge.
You never commit without reviewing the diff first. The human is always the final
gatekeeper — the agent's job is to surface candidates, not to decide what gets
promoted to long-term memory.
When to use
- After a long session with many captures
- When the user asks to "consolidate", "summarise", or "clean up" memories
- Periodic maintenance (e.g. end of week)
Workflow
Always propose before applying:
# Step 1 — generate proposals (written to vault inbox for review)
vault-cli consolidate --propose [--project <id>]
# Step 2 — open vault inbox, review, set status: approved or rejected
# (edit 00-inbox/consolidation-proposals.md in Obsidian)
# Step 3 — apply approved proposals
vault-cli consolidate --apply
If --propose outputs "No episodic memories found to consolidate", skip Step 3 —
there is nothing to apply.
What happens
--propose: clusters episodic memories by semantic similarity, calls the inference command to synthesise each cluster, writes proposals to00-inbox/consolidation-proposals.md--apply: reads the proposals file, writes approved ones as semantic notes, marks source episodics assuperseded, logs rejected ones to audit
Important
Source episodic memories are never deleted — only marked superseded.
Human edits in Obsidian are always respected and never overwritten.
Never
- Never run
--applywithout first running--propose— doing so bypasses human review and irreversibly promotes unreviewed clusters to semantic memory - Never run
--applywithout confirming the user has reviewed the proposals — always pause at Step 2 and wait for the user to confirm before proceeding - Never delete episodic source memories manually — they are preserved automatically and serve as audit history
What ships with it: 18 files
9.8 KB alongside SKILL.md
evals/
- instructions.json2.5 KB
- scenario-1/capability.txt13 B
- scenario-1/criteria.json1.4 KB
- scenario-1/task.md307 B
- scenario-2/capability.txt15 B
- scenario-2/criteria.json943 B
- scenario-2/task.md271 B
- scenario-3/capability.txt18 B
- scenario-3/criteria.json1.1 KB
- scenario-3/task.md279 B
- scenario-4/capability.txt21 B
- scenario-4/criteria.json1.1 KB
- scenario-4/task.md300 B
- scenario-5/capability.txt19 B
- scenario-5/criteria.json1.1 KB
- scenario-5/task.md287 B
- summary_infeasible.json58 B
- summary.json246 B