cleanup

A command for clearing promoted notes from an agent’s .memory/ directory. It checks the notes, warns about items not yet promoted, asks for confirmation, and keeps the file headers.

In plain words
What is it for?
Use it to review and clear todos, decisions, and questions stored in .memory/. It can also warn when notes have not been moved into longer-term records.
Why use it?
It helps remove old working notes while showing what will be deleted and warning that the action cannot be undone.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/backchainai/backchain-plugins/cleanup
Clone the repo
git clone --depth 1 https://github.com/backchainai/backchain-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00426
Opus 5 $0.00000 $0.00213
Sonnet 5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash 4b093b393435, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

engram/skills/working/commands/cleanup.md · 69 lines

What it actually says

Command: cleanup

Delete promoted content from the .memory/ directory.

Trigger

/engram:working cleanup or natural language: "clean up working memory", "clear memory".

Behavior

  1. Verify .memory/ exists in the current directory.
  2. Read and display current contents (item counts per file).
  3. Check whether promotion has happened (warn if not).
  4. Request explicit user confirmation.
  5. Delete file contents (keep the directory and the file headers).
  6. Confirm.

Pre-cleanup check

Before deleting, show what will be removed:

Current .memory/ contents:
- todos.md: 5 items (2 in-progress, 1 blocked, 2 completed)
- decisions.md: 3 decisions
- questions.md: 2 questions (1 resolved, 1 unresolved)

This action cannot be undone. Delete all contents?

Promotion warning

If unpromoted items exist:

Warning: .memory/ contains items that have not been promoted:
- 2 decisions (no corresponding ADRs)
- 1 unresolved question (no issue created)

Run /engram:working promote first, or confirm deletion to proceed.

Require explicit confirmation to delete unpromoted content.

Cleanup actions

For each file, delete contents but preserve a single header line:

  • todos.md → keep # Action Items
  • decisions.md → keep # Decisions
  • questions.md → keep # Open Questions

Keep the .memory/ directory itself. Its presence signals that this project uses working memory; only the contents get cleared.

Output format

Working memory cleaned up:
- Deleted 5 todos, 3 decisions, 2 questions
- Directory .memory/ preserved for future use

Constraints

  • Always require explicit user confirmation.
  • Warn about unpromoted content.
  • Never delete the .memory/ directory itself.
  • Keep file headers intact (ready for the next checkpoint).
  • Action is irreversible (no archive mode in v1).
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 69 lines · 0 tokens per session scan A 4b093b393435

Subscribe to this mod's changes

cleanup is a command published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 426 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.