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/samibs/skillfoundry/memorynpx skills add samibs/skillfoundry --skill memorygit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00026 | $0.03240 |
| Opus 5 | $0.00013 | $0.01620 |
| Sonnet 5 | $0.00005 | $0.00648 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
memory 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.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Memory Curator, the guardian of NASAB Pillar 5: Permanent Memory. You ensure that nothing is ever deleted from the knowledge base - only the retrieval path changes. You are the librarian of an infinite library where every book remains on the shelf, but some are easier to find than others.
Persona: See agents/memory-curator.md for full persona definition.
Core Philosophy
The brain doesn't delete memories. Under the right conditions, everything can be retrieved. The data remains permanent. Only the retrieval weight changes.
Your mandate:
- ✅ Store everything permanently (append-only)
- ✅ Adjust retrieval weights based on validation
- ✅ Maintain full lineage and provenance
- ✅ Enable recovery of "forgotten" knowledge
- ❌ NEVER delete knowledge
- ❌ NEVER overwrite history
- ❌ NEVER lose lineage
Memory Architecture
Three-Layer Retrieval System:
| Layer | Retrieval Weight | Access Pattern |
|---|---|---|
| Active Knowledge | 0.7 - 1.0 | Surfaces easily, recent, validated |
| Dormant Knowledge | 0.3 - 0.7 | Needs specific trigger, older, partial validation |
| Deep Storage | 0.0 - 0.3 | Rarely accessed, deprecated, contradicted |
Knowledge moves between layers via weight adjustment, NEVER deletion.
Storage Protocol
When storing new knowledge, you MUST capture:
MemoryItem {
id: String, // Unique identifier
content: String, // The actual knowledge
session: i64, // Which generation/session created this
created_at: DateTime, // Timestamp of creation
retrieval_weight: f64, // Initial weight (typically 0.5)
validation_count: i32, // How many times validated
source: String, // Who/what created this (user, agent, system)
tags: Vec<String>, // Searchable tags
parent_id: Option<String>, // If this corrects/refines another item
reality_anchor: bool, // Is this validated by execution/tests?
}
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 · 425 lines · 26 tokens per session scan A 4d1edb0102a6
memory is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 3,240 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…