digest

digest is a skill for Claude Code from wrg32786/aigent-os. It costs 32 tokens per session (344 once invoked), scanned A, original, MIT.

A memory-curation workflow that reviews staged candidates in a memory file and lets an operator promote, skip, supersede, or defer each one.

In plain words
What is it for?
It helps maintain a memory vault by reviewing decisions, preferences, project facts, people, and other stored knowledge.
Why use it?
It prevents unreviewed information from being added automatically to an agent’s long-term memory.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

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 skills/wrg32786/aigent-os/digest
Any agent
npx skills add wrg32786/aigent-os --skill digest
Clone the repo
git clone --depth 1 https://github.com/wrg32786/aigent-os

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for digest

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrg32786/aigent-os/digest.svg)](https://agentmods.dev/skills/wrg32786/aigent-os/digest)
Your own site
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/digest"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/digest.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 344 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 5.1 $0.00032 $0.00344
Opus 5 $0.00016 $0.00172
Sonnet 5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash f560e340c875, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 4d 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.

skills/digest/SKILL.md · 41 lines

What it actually says

/digest

Background curation tier. Reviews staged candidates and asks the operator to:

  • promote → write to suggested destination (concepts/, decisions/, etc.)
  • skip → mark status: skipped, leave in ledger
  • supersede → strike + replace an existing vault entry

When to run

  • At /close (auto, surface candidates)
  • When /body-check reports memory_candidate_backlog > 10
  • Manually when the operator asks
  • On the documented seven-day vault-maintenance cadence

Behavior

  1. Read vault/memory/MEMORY_CANDIDATES.md (or the documented memory/ fallback). Filter exact status: staged rows.
  2. Group by type (decision / preference / doctrine / project / person / skill).
  3. Surface each group to the operator: source phrase, suggested destination, confidence.
  4. For each, the operator answers in one word: promote / skip / supersede / defer.
  5. Apply the action. Update status and digested_on fields.

NEVER auto-promote. Only act on the operator's word.

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. 4d ago First seen · 41 lines · 32 tokens per session scan A f560e340c875

Subscribe to this mod's changes

digest is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 344 once invoked, about $0.0002 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 2026-09-01.