midmem-research-digest

midmem-research-digest is a skill for Claude Code, Codex from U4CSolutions/MidMem. It costs 98 tokens per session (835 once invoked), scanned A, original, Apache-2.0.

A workflow for turning recurring research reports, such as weekly arXiv reviews, into a checked and published digest for MidMem, a knowledge store.

In plain words
What is it for?
It helps ingest reports, compare each recommendation with the implemented system, publish findings, and update the roadmap.
Why use it?
It prevents recommendations from being accepted without checking them against the actual source code. It also records the confirmed changes in the project roadmap.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps ingest reports, compare each recommendation with the implemented system, publish…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/u4csolutions/midmem/midmem-research-digest
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.

Any agent
npx skills add U4CSolutions/MidMem --skill midmem-research-digest
Clone the repo
git clone --depth 1 https://github.com/U4CSolutions/MidMem

Made for: Claude Code, Codex.

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 midmem-research-digest

README.md
[![agentmods](https://agentmods.dev/badge/skills/u4csolutions/midmem/midmem-research-digest.svg)](https://agentmods.dev/skills/u4csolutions/midmem/midmem-research-digest)
Your own site
<a href="https://agentmods.dev/skills/u4csolutions/midmem/midmem-research-digest"><img src="https://agentmods.dev/badge/skills/u4csolutions/midmem/midmem-research-digest.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 835 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00098 $0.00835
Opus 5 $0.00049 $0.00417
Sonnet 5 $0.00020 $0.00167
Haiku 4.5 $0.00010 $0.00084

Measured 6d ago against content hash 14b0c97fd9f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

midmem-research-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 6d 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/midmem-research-digest/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MidMem Research Digest — from report to roadmap, grounded

A research digest is an LLM-written synthesis. Its value is only realized when each recommendation is checked against what the store ACTUALLY implements (DELEGATE-52 discipline) and the deltas land in the roadmap. Never let a report grade your system by itself — its "you should have X" claims are hypotheses to verify, not facts.

Procedure

  1. Intake via midmem-ingest (authoritative for staging rules): stage the report, build a citations manifest (canonical paper ids, dedup against the store), ingest --scope shared --type research, read the grounding numbers — note the CLI summary may print only {"success": true}; the authoritative record is the log table row operation='ingest' (summaryScore, concepts, claims, quarantined) in state.db — then run the recall check.
  2. Ground-check every "the system should…" recommendation against the source at packages/core/src/ — targeted greps beat reading: memory typing (memFunction), claim verbs (supersede|contradict), ledger states (pending|quarantine|deferred), provenance/authority (provenance|trust|authority), graph shape (communit|parent), retrieval gating (sufficien|progressive). Sort every recommendation into exactly one bucket: already-have (cite the evidence) / partial (what exists, what's missing) / new gap / explicitly-not-adopting (say why — e.g. filesystem-taxonomy ideas don't apply to a DB-as-truth + projected-wiki design).
  3. Write the digest where your operator reads documents. Structure: headline (what this report validates or overturns about the architecture) → already-have (with code evidence) → gaps as a priority-ordered roadmap candidate list (effort + which existing subsystem each fits) → explicitly-not-adopting → paper shortlist for deeper follow-up.
  4. Record roadmap deltas in the repo (docs/ROADMAP-*.md or equivalent): one increment row per new gap, tagged with the paper id and the design principle. Do NOT start code changes from a digest — midmem-dev owns implementation when an item is picked up.
  5. Record the run in your system of record: source id, grounding numbers, digest location, count of roadmap candidates.

Read the full file on GitHub · 56 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. 6d ago First seen · 56 lines · 98 tokens per session scan A 14b0c97fd9f6

Subscribe to this mod's changes

midmem-research-digest is a skill published in the GitHub repository U4CSolutions/MidMem (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 98 tokens to every session and 835 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

lemmalog

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…

JordyZomer/lemmalog · 105 tokens

autograph

Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…

smixs/agent-second-brain · 89 tokens

dbrain-processor

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

smixs/agent-second-brain · 60 tokens

braindb

Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.

dimknaf/braindb · 36 tokens

braindb-agent

Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.

dimknaf/braindb · 40 tokens

braindb-custom-profile

How to author a BrainDB custom profile — prompt add/replace fragments and an optional keyless ingestor — that shapes wiki naming/structure and feeds a custom ingestion source, with zero effect on defaults when inactive.

dimknaf/braindb · 49 tokens