claude

memory-engineering

Name: memory-engineering
Author: Matt Corbett

Memory engineering team — agents (memory-architect-lead, memory-retention-and-erasure-engineer, memory-eval-cost-analyst) for the decisions behind a durable memory store: what earns a write, which paradigm, which surface holds the bytes, what makes it forget, what a delete leaves behind, cost per correct answer. skills, commands, dated knowledge files, best-practices, templates, scenarios, an advisory hook, a stdlib calculator. Advisory only — it never reads or mutates a real store. Seams: ai-agent-engineering decides whether an agent should remember at all and where state sits in its topology, this engineers the memory system itself; ai-red-teaming owns the ASI06 attack taxonomy and offensive testing, this owns the defensive design half; data-governance-privacy owns DSAR and legal basis, this owns erasure residue in embeddings and version history; retrieval → ai-rag-engineering; evals → llm-evaluation-engineering; the Claude app → claude-app-engineering. Requires ravenclaude-core@>=0.238.0.

9 on GitHubby Matt Corbettv0.1.4MITupdated today

Plugin memory-engineering from marketplace ravenclaude in mcorbett51090/RavenClaude. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (6)

budget-memory-costs
Put a defensible number on a memory system — break-even against a named baseline, growth and caps, cache-invalidation cost, and cost per correct answer. Reach for this on any pay-for-itself question.
build-memory-eval
Prove a memory system earns its write path — golden set with provenance, judged failure modes, the runnable bake-off, and cost per correct answer. Reach for this before adopting, replacing or retiring any memory system.
choose-memory-paradigm
Decide whether to build a memory system at all, and if so which paradigm — raw context, flat retrieval, LLM-extraction or agentic — behind a mandatory baseline-first gate. Reach for this before any memory design work.
design-forgetting-policy
Design retention and erasure before the first write — TTL, caps, decay, consolidation timing, dedup, contradiction handling, and what a delete actually leaves behind. Reach for this on any durable store.
map-memory-surface
Name the storage surface a write actually lands on — who holds the bytes, who executes the write, and what trust model comes with it. Reach for this before writing any memory design down.
memory-poisoning-review
Audit an agent's durable memory for poisoning risk and harden it against OWASP ASI06 — enumerate write paths reachable from untrusted input, classify read-only vs read-write, verify audit and rollback. Reach for this when a diff touches a memory store.

Slash commands (6)

/memory-engineering:budget-memory-costs
Put a defensible number on a memory system — break-even against a named baseline, growth and caps, cache-invalidation cost, and cost per correct answer. Reach for this on a pay-for-itself question.
/memory-engineering:build-memory-eval
Prove a memory system earns its write path — golden set with provenance, judged failure modes, the runnable bake-off, and cost per correct answer. Reach for this before adopting or retiring any memory system.
/memory-engineering:choose-memory-paradigm
Decide whether to build a memory system at all, and if so which paradigm, behind a mandatory baseline-first gate. Reach for this before any memory design work.
/memory-engineering:design-forgetting-policy
Design retention and erasure before the first write — TTL, caps, consolidation timing, dedup, contradiction handling, and what a delete leaves behind. Reach for this on any durable store.
/memory-engineering:map-memory-surface
Name the storage surface a write lands on — who holds the bytes, who executes the write, and the trust model that comes with it. Reach for this before writing any memory design down.
/memory-engineering:memory-poisoning-review
Audit an agent's durable memory for poisoning risk and harden it against OWASP ASI06 — write paths reachable from untrusted input, read-only classification, audit and rollback. Reach for this when a diff touches a memory store.

Subagents (3)

memory-architect-lead
Design agent memory: what earns a write, which paradigm (raw context / flat retrieval / LLM-extraction / agentic), which surface holds the bytes, and the write-path trust boundary and poisoning exposure. First contact; routes to siblings. NOT corpus retrieval → ai-rag-engineering.
memory-eval-cost-analyst
Prove a memory system earns its write path: golden set, judged failure modes, staleness and contradiction, cost per correct answer, break-even against a named baseline. NOT generic LLM eval harnesses → llm-evaluation-engineering.
memory-retention-and-erasure-engineer
Forgetting, consolidation and erasure for a durable memory store: TTL and size caps, write-path vs offline consolidation, contradiction and staleness, and what survives a delete (versions, embeddings, summaries). NOT a legal/DSAR determination → data-governance-privacy.

Hooks (1)

PostToolUse
/usr/bin/env -u BASH_ENV -u ENV -u SHELLOPTS -u BASHOPTS -u LD_PRELOAD -u LD_LIBRARY_PATH -u LD_AUDIT -u DYLD_INSERT_LIBRARIES -u DYLD_LIBRARY_PATH -u PYTHONPATH -u PYTHONSTARTUP PATH=/usr/local/bin:/

View source on GitHub mcorbett51090.github.io

More from mcorbett51090/RavenClaude

All 184 plugins →

RavenClaude Core

claude

Domain-neutral Claude Code foundation: specialist agents, skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), /wireframe (describe anything → validated model + high-fi Artifact + Mermaid), Problems & Resolutions view, declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer), and Claude orchestrator escape hatch (/claude-orchestrate). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /wireframe, /reset-plugin-cache, /handoff.

70 skills · 14 commands · 18 agents · hooks

power-platform

claude

Power Platform specialist team — agents (incl. power-platform-tester, power-bi-engineer) and skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional], main-forms-are-Web-API-authorable grounding) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.

24 skills · 8 commands · 11 agents · 1 MCP server · hooks

finance

claude

Corporate finance & FP&A specialist team — FP&A analyst (budgets, forecasts, variance commentary), financial modeler (3-statement, DCF, scenarios), controller (close, JEs, reconciliations), treasury analyst (cash, covenants, FX), valuation analyst (DCF + comps + precedent), audit-prep specialist (PBC, walkthroughs, SOC1/2 narratives), and board-pack composer. skills incl. a gold-standard NetSuite close (OAuth2 M2M + SuiteQL BS/IS trial balance, layperson runbook), templates, a knowledge bank (ASC 805 / 718 / 740, accrual-cutoff, WACC, cost accounting, FP&A operating model + decision support, NetSuite integration landscape), advisory hooks (hardcoded rates / plaintext PII / missing Sources / Assumptions; secrets-PII scan). Inherits ravenclaude-core protocols.

23 skills · 7 commands · 7 agents · hooks

web-design

claude

Web design & build specialist team — web architect (IA, stack, hosting), UX designer (wireframes, flows, conversion), visual designer (brand, typography, tokens), frontend implementer (HTML/CSS/JS, React, Astro, Next), content strategist (copy, microcopy, SEO content), accessibility auditor (WCAG 2.2 AA/AAA), and performance engineer (Core Web Vitals, image/font optimization). skills (the gold-standard-website-pipeline gated build pipeline, static-site build, design-system audit, card/tile UI, accessibility review, Core Web Vitals tuning, technical SEO audit, information architecture, conversion design, content audit, design-tokens scaffolding, third-party hygiene, Fluent UI v9 + React implementation), templates, an advisory hook, and a knowledge bank seeded with a curated 2026 reference set of "cutting edge yet simple" marketing-site donors — the design agents carry compact inline priors plus a pointer to the full brief. Inherits ravenclaude-core protocols.

19 skills · 7 commands · 7 agents · hooks · LSP

edtech-partner-success

claude

EdTech-flavored Partner Success Manager team — specialist agents anchored on the PSM lane, with skills, templates, an advisory hook, a knowledge bank with Mermaid decision trees, a engagement bank, and a stdlib psm_calc.py calculator (seat-utilization / renewal-NRR-forecast / time-to-value). Covers QBRs, success plans, health scores, a self-contained Power-BI-style partner-health report, onboarding, touchpoint logs, adoption sequencing, 90-day implementation arcs, train-the-trainer curricula, advocacy/reference pipelines, renewal decision memos, and the integration contract for a centralized CS dashboard (Planhat + Salesforce + Snowflake + Zapier + Granola). Team growth ships as skills + knowledge + templates, not parallel agents. Primary-source citations with retrieval dates. Vertical-explicit but segment-agnostic — fits K-12, higher-ed, corporate L&D, or mixed EdTech books. Inherits ravenclaude-core protocols including the alternate-methods Capability Grounding Protocol.

17 skills · 5 commands · 6 agents · hooks

regulatory-compliance

claude

Financial-regulatory & compliance specialist team — function agents (AML/KYC, regulatory-reporting, risk-and-controls, policy & procedure, examination-prep, Bermuda-insurance) PLUS jurisdiction/regulator specialists: BMA financial-institutions (banking, trust, corporate-services, fund-admin, investment-business, money-service, digital-assets — the primary build-out, with deep AML/ATF + supervision/fees + licensing-classification trees), CIMA (Cayman), Bahamas, Channel Islands (Jersey JFSC + Guernsey GFSC), UK PRA, and US federal+state. primary-source-cited regulator knowledge files, best-practice rules, skills, templates, a defensive PreToolUse hook (PII scrub — SSN/IBAN/credit-card/Bermuda TIN/wire instructions). Positioning reflects field experience inside a Tier-1 financial regulator (BMA). Inherits ravenclaude-core protocols.

11 skills · 5 commands · 12 agents · hooks

Similar plugins

openviking-memory

claudecodex

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks

volcengine/OpenViking 42,126

agent-memory

claude

A four-tier memory ladder for Claude Code where promotion is earned by recurrence, not asserted by confidence. L0 raw transcripts are never injected; L1 candidate atoms are gitignored and recalled on lexical relevance per prompt; L2 project context loads each session start; L3 stable persona is always loaded. L1 to L2 needs three distinct sessions spanning two distinct calendar days (a stated claim needs two; a verified claim is the only single-observation path); L2 to L3 needs two projects and thirty days. Two gates refuse rather than guess: a claim altered by the redaction pass never promotes on evidence alone, and a contradicted claim freezes until a human resolves it. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt. Ships 5 stdlib scripts, 3 hooks, a cs-memory-curator agent, /cs-memory, a JSON schema, and a 69-check validator. Concept from TencentCloud/TencentDB-Agent-Memory (MIT); no upstream code included.

1 skill · 1 command · 1 agent · hooks

alirezarezvani/claude-skills 29,725

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

planning-with-files

claudecodex

Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.

6 skills · 13 commands · hooks

OthmanAdi/planning-with-files 28,031

pm-data-analytics

claude

Data analytics skills for PMs: SQL query generation and cohort analysis. Analyze user data, generate queries, and identify retention patterns.

3 skills · 3 commands

phuryn/pm-skills 27,939

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain memory-engineering?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins184 plugins