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.
npx skills add U4CSolutions/MidMem --skill midmem-ingest-reviewgit clone --depth 1 https://github.com/U4CSolutions/MidMemWrote 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.
[](https://agentmods.dev/skills/u4csolutions/midmem/midmem-ingest-review)<a href="https://agentmods.dev/skills/u4csolutions/midmem/midmem-ingest-review"><img src="https://agentmods.dev/badge/skills/u4csolutions/midmem/midmem-ingest-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/u4csolutions/midmem/midmem-ingest-review"><img src="https://agentmods.dev/badge/skills/u4csolutions/midmem/midmem-ingest-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.00915 |
| Opus 5 | $0.00055 | $0.00458 |
| Sonnet 5 | $0.00022 | $0.00183 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
midmem-ingest-review 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MidMem Ingest & Review — knowledge quality + cross-stack check-and-balance
Two jobs: (1) ingest new knowledge cleanly, (2) audit the store and the two stacks' understanding of it. The premise (DELEGATE-52): models confabulate and drift silently and will confidently assert faithfulness — so judge quality by deterministic signals + cross-stack agreement, never by asking a model "is this right?"
Ingest (with verification, not blind)
midmem ingest <path> --scope <openclaw|hermes|shared> [--type ...]. Grounding runs automatically.- Read the grounding report in the result (
summaryScore,conceptsKept/Quarantined,claimsKept/Quarantined). Flags: lowsummaryScore(≲0.4) → the summary drifted from the source; heavy quarantine → the extractor confabulated. Investigate the source/extraction before trusting it. - Finish editing a source BEFORE ingesting (mid-edit saves mint duplicates). Re-ingest supersedes.
Review / audit the store
midmem brief— tier distribution, vector health (dim, fallback count), recent ops.midmem audit— contradictions + orphan concepts (deterministic verifier). Triage each.- Per-entry quality:
midmem recall <id>→ checkprovenance.grounding,trust_score,retrieval_count, tier. Low grounding or low trust + low usage = decay/forget candidate.
Cross-stack check-and-balance (the core differentiator)
The store is shared but each stack reads its own scope + shared. To compare what each
understands about a topic, run the same query under each lens and diff:
midmem query "<topic>" --scopes openclaw,shared # what OpenClaw can surface
midmem query "<topic>" --scopes hermes,shared # what Hermes can surface
Then assess:
- Divergence — entries one stack has and the other doesn't (private-scope knowledge that should
be
shared? or stale to one side?). - Contradiction — the two return conflicting claims → flag; reconcile to the source.
- Grounding/assumption gaps — a surfaced claim whose
provenance.groundingis low, or that isn't in the cited source → an assumption the system is treating as fact. Surface it explicitly. - Scope leakage — private-scope content that's actually general (promote to
shared) or shared content that's stack-specific.
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.
- 9d ago First seen · 60 lines · 110 tokens per session scan A 89b6438b98cf
midmem-ingest-review is a skill published in the GitHub repository U4CSolutions/MidMem (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 110 tokens to every session and 915 once invoked, about $0.0006 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.
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…
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.
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.
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…
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.
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.