promote

A command for moving temporary .memory/ project notes into permanent knowledge locations. It reviews todos, decisions, and questions before asking where each item should go.

In plain words
What is it for?
Promoting decisions to architecture decision records or smaller project context to an auto-memory location.
Why use it?
It turns working notes into lasting project documentation or memory after the user approves the plan.

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/promote
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 867 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 $0.00867
Opus 5 $0.00000 $0.00434
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00087

Measured 2d ago against content hash 328fdfd43a8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

promote 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/promote.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: promote

Move .memory/ artifacts to permanent knowledge locations.

Trigger

/engram:working promote or natural language: "promote working memory", "move memory to permanent".

Behavior

  1. Verify .memory/ exists in the current directory.
  2. Read all .memory/ files (todos.md, decisions.md, questions.md).
  3. Analyze each artifact and prompt the user to confirm the promotion target. Do not assume a specific tool.
  4. Present the full plan for review.
  5. Execute approved promotions.
  6. Report results.

Promotion analysis

Decisions → ADRs or auto memory

For each decision in decisions.md, classify by significance:

ADR-worthy (significant architectural / design choice):

  1. Detect a likely ADR location (docs/adr/ if present). Otherwise ask the user where ADRs live in this project.
  2. Determine the next ADR number by scanning existing ADRs.
  3. Format using the project's ADR template if one exists, otherwise a standard one (context, decision, rationale, consequences).

Auto-memory-worthy (project context worth remembering, but too small for an ADR):

  1. Write to a new file in the auto-memory directory (~/.claude/projects/<project>/memory/).
  2. Use the auto-memory frontmatter format (name, description, type: project).
  3. Add a one-line pointer in MEMORY.md if the user has set up an index — confirm with the user before modifying it.

Skip trivial decisions (tool version choices, formatting preferences). Auto memory captures these organically; promoting them is noise.

Todos → issues

For each incomplete todo in todos.md:

  1. Detect the user's issue tracker from project signals. If undetected or ambiguous, ask once for the session: "Which issue tracker should I use? (Beads, Linear, GitHub Issues, other)"
  2. Suggest issue type, priority, and labels based on the todo content. Confirm before creating.
  3. Create the issue using the tool's standard CLI or API.

Skip:

  • Completed todos (already done).
  • Trivial items (handle inline).

Read the full file on GitHub · 102 lines

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 · 102 lines · 0 tokens per session scan A 328fdfd43a8d

Subscribe to this mod's changes

promote 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 867 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.