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/rasputinkaiser/self-improvement-plugin/sips-memory-fabricnpx skills add RasputinKaiser/Self-Improvement-Plugin --skill sips-memory-fabricgit clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWrote 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/rasputinkaiser/self-improvement-plugin/sips-memory-fabric)<a href="https://agentmods.dev/skills/rasputinkaiser/self-improvement-plugin/sips-memory-fabric"><img src="https://agentmods.dev/badge/skills/rasputinkaiser/self-improvement-plugin/sips-memory-fabric.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00251 |
| Opus 5 | $0.00026 | $0.00125 |
| Sonnet 5 | $0.00010 | $0.00050 |
| Haiku 4.5 | $0.00005 | $0.00025 |
Grade A, and why
sips-memory-fabric 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.
What it actually says
SIPS Memory Fabric
Use homebase_recall with the user's query and current repo root. Treat Memory Fabric as a SIPS-owned subsystem for recall, lesson capture, memory health, and future tooling.
Do not present recall as current proof. If a memory-derived fact is likely to drift, verify it with local files or runtime checks before using it as evidence.
When recall finds a relevant fix, cite the remembered boundary in the final answer and run the live command that proves the current repo still matches it.
After fixing any bump (failed command, wrong path, retry chain), record it immediately: run python3 scripts/memory_fabric_cli.py record from the SIPS plugin root with the symptom, the working fix, and repo scope (or memory_fabric_record on the codex-memory-fabric MCP when that host exposes it), then confirm it surfaces via homebase_recall. Unrecorded fixes recur across sessions.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 15 lines · 51 tokens per session scan A 4fd183ea9faf
sips-memory-fabric is a skill published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (8 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 251 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
journal
Maintain agent-authored investigation memory over Genomi evidence links, reviewed source findings, decisions, contradictions, and unresolved questions.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
claude-compaction-restore
Use when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /compact, or needs to rebuild its working mental model from Claude JSONL transcripts and touched files.
agentic-os
OpenAI Codex 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
agent-common
Shared preamble loaded by all cc10x agents — memory protocol, contract format, output rules.