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 agentmods add skills/u4csolutions/midmem/midmem-pattern-capturenpx skills add U4CSolutions/MidMem --skill midmem-pattern-capturegit clone --depth 1 https://github.com/U4CSolutions/MidMemWhat 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 | $0.00070 | $0.00472 |
| Opus 5 | $0.00035 | $0.00236 |
| Sonnet 5 | $0.00014 | $0.00094 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
midmem-pattern-capture 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.
What it actually says
Pattern capture — record what builds prove
Capture packs make MidMem domain-extensible as data: a pack registers entry types (with a
persistence tier + memory function + graph edge), categorizer rules and an edge vocabulary.
The shipped coding-patterns pack covers: pattern, scaffold, anti-pattern, recipe
(all procedural-function, memory-tier).
When to capture
- At the moment of proof, not from memory: a card/QA gate just passed using an approach worth reusing → record it NOW with its evidence link (commit hash, repo, card id).
- A debugging approach failed for a reproducible reason →
anti-patternwith the failure as evidence. Dead ends prevent repeats; that is their entire value. - The same scaffold got copied into a second project →
scaffold, evidence both repos.
How
midmem pattern --type pattern --title "<short name>" \
--context "<where this applies>" --problem "<what it solves>" \
--solution "<the approach>" --evidence "<repo@hash;card-id>" [--scope shared]
(MCP: record_pattern; list registered types with midmem packs.)
Rules
- Evidence is required in spirit: a pattern without a commit/repo/run reference is an opinion. Link the proof.
- Never hand-promote. Patterns start at memory tier; retrieval renewals during later builds are what earn wisdom. A "best practice" nobody re-uses should decay.
- Anti-patterns are captures, not shame: record the failure mode plainly; the dead-end demotion in retrieval surfaces them as warnings automatically.
- New domains = new pack JSON (entry types + rules + edges), registered via
MIDMEM_CAPTURE_PACKS— never a core code change. Packs cannot redefine core types.
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.
- 2d ago First seen · 37 lines · 70 tokens per session scan A fdf7022d30f3
midmem-pattern-capture is a skill published in the GitHub repository U4CSolutions/MidMem (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 70 tokens to every session and 472 once invoked, about $0.0003 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
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
obsidian-layout-adjustment
Workflow for working with the user on changing how Obsidian looks using CSS snippets. Use this whenever the user asks to restyle Obsidian, tune a vault's visual layout, adjust tabs, sidebars, note surfaces, properties, backlinks, graph panes, file explorer rows, icons, links, shadows, active states, or CSS snippets.…
alfworld-locate-target-object
Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g., "potato", "plate") and its location is not immediately known. Moves to a relevant receptacle (like a fridge or cabinet), checks its contents, and outputs the object's location or confirms its…
scienceworld-growth-focuser
Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…