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/kitfunso/hippo-memory/memorynpx skills add kitfunso/hippo-memory --skill memorygit clone --depth 1 https://github.com/kitfunso/hippo-memoryWhat 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 | $0.00044 | $0.00442 |
| Opus 5 | $0.00022 | $0.00221 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
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.
What it actually says
Hippo Memory
This project uses Hippo for biologically-inspired memory across sessions. Memories decay over time unless retrieved. Errors stick longer. Sleep consolidates.
At session start (MANDATORY)
Before doing any work, load relevant context:
hippo context --auto --budget 1500
Read the output. These are things the project has learned from past sessions.
When you learn something non-obvious
hippo remember "<the lesson in 1-2 sentences>" --tag <category>
When you hit an error or unexpected failure
hippo remember "<what failed, why, and how you fixed it>" --error
The --error flag doubles the half-life. Hard lessons don't fade quietly.
After completing work successfully
hippo outcome --good
If the recalled memories were irrelevant:
hippo outcome --bad
When stuck or hitting repeated errors
hippo recall "<what's going wrong>" --budget 2000 --why
When making an architectural decision
hippo decide "<decision>" --context "<why>"
Decisions get a 90-day half-life and a recall boost so they surface when relevant.
When migrating or replacing a tool
hippo invalidate "<old tool>" --reason "migrated to <new tool>"
Or let hippo learn --git detect it automatically from migration commits.
After significant coding sessions
hippo learn --git
This scans recent commits, auto-extracts lessons, and invalidates memories about replaced tools.
Export memories
hippo export memories.json
hippo export --format markdown memories.md
Check memory health
hippo status
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 · 89 lines · 44 tokens per session scan A 876a5a4ead80
memory is a skill published in the GitHub repository kitfunso/hippo-memory (734 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 442 once invoked, about $0.0002 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.