digest

A command that explicitly imports a repository's current code and documentation into its Engram memory graph.

In plain words
What is it for?
Running Engram's project-digestion workflow, including scanning for FIXME and TODO markers, writing reasoning nodes, and pointing to the graph pane.
Why use it?
It turns a one-time request to record project reasoning into a defined digestion process with setup checks and a completion summary.

Command

Part of the engram plugin — 2 skills, 3 commands shipped together

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/techtheist/engram/digest
Clone the repo
git clone --depth 1 https://github.com/techtheist/engram

Or install engram, the plugin that ships this one along with the rest of its 2 skills, 3 commands.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 190 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 $0.00023 $0.00190
Opus 5 $0.00012 $0.00095
Sonnet 5 $0.00005 $0.00038
Haiku 4.5 $0.00002 $0.00019

Measured 3d ago against content hash 87631560b2ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

digest 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 3d 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.

claude-plugin/commands/digest.md · 12 lines

What it actually says

The user wants this project digested into its Engram memory graph.

Invoke the engram-digest skill and follow it end to end: preflight the wiring, run the offline FIXME/TODO scan via the daemon's POST /digest/scan, read the project's reasoning surfaces, author nodes per the skill's worked examples under a single digest-<YYYY-MM-DD> session id, act on every write verdict, and finish with an audible summary plus a pointer to the pane.

If the engram MCP tools are not available in this session, stop and run /engram:setup first — never digest into an unwired repo.

$ARGUMENTS names a narrower scope (a directory or subsystem) when present; otherwise digest the whole working tree.

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. 3d ago First seen · 12 lines · 23 tokens per session scan A 87631560b2ff

Subscribe to this mod's changes

digest is a command published in the GitHub repository techtheist/engram (17 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 190 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.