Borrowing it
Nothing to install: this file belongs to onceMisery/seahorse-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/onceMisery/seahorse-agent/main/.skills/seahorse-memory-system-audit/SKILL.mdgit clone --depth 1 https://github.com/onceMisery/seahorse-agentWrote 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/oncemisery/seahorse-agent/seahorse-memory-system-audit)<a href="https://agentmods.dev/skills/oncemisery/seahorse-agent/seahorse-memory-system-audit"><img src="https://agentmods.dev/badge/skills/oncemisery/seahorse-agent/seahorse-memory-system-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oncemisery/seahorse-agent/seahorse-memory-system-audit"><img src="https://agentmods.dev/badge/skills/oncemisery/seahorse-agent/seahorse-memory-system-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.01023 |
| Opus 5 | $0.00026 | $0.00511 |
| Sonnet 5 | $0.00010 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
seahorse-memory-system-audit 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seahorse Memory System Audit
Overview
Audit Seahorse memory work against the project memory design, without collapsing the four canonical memory layers or hard-coding Gemini behavior. Focus on architecture boundaries, review safety, recall quality, persistence correctness, and focused test evidence.
Start Set
Use the user-specified branch/worktree first. Then locate only the relevant docs:
rg --files docs | rg "gemini-design|Gemini|memory|记忆|handoff|memory-gemini|default-memory"
Common anchors:
docs/gemini-design.mddocs/aegis/work/2026-05-23-memory-gemini-handoff/HANDOFF.mddocs/aegis/plans/*memory*.mddocs/aegis/specs/*memory*.md- Chinese Gemini memory design and gap documents under
docs/.
Scope Decision
Name the slice before auditing. Typical slices are:
- Ingestion/refiner/write pipeline.
- REVIEW candidate query, decision, feedback, and concurrency.
- Recall pipeline, keyword/vector/graph channels, reranking, and golden cases.
- Maintenance, lifecycle, GC, alias merge, outbox, and trace recording.
- Privacy/governance APIs and user memory center.
- JDBC/cache adapter persistence and Spring auto-configuration.
Invariants
Keep these non-negotiable unless the user explicitly changes the design:
- Four memory layers remain canonical:
WORKING,SHORT_TERM,LONG_TERM,SEMANTIC. - Kernel depends on domain objects and ports, not Spring/JDBC/Web.
- Gemini-like behavior is pluggable through ports; do not make Gemini a hard dependency.
- Status/type/reason/source/risk values use enums or named constants.
- Domain objects maintain invariants; application services orchestrate; repository adapters persist/query.
- REVIEW decisions must be stale-safe and double-review-safe. Avoid side effects before the candidate state is claimed or otherwise made idempotent.
- Recall fallbacks must be explicit; missing vector/graph/keyword implementations are product gaps, not silent success.
- Privacy and tenant/user scoping must be enforced at query and write boundaries.
What ships with it
1 file 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.
- 12d ago First seen · 106 lines · 52 tokens per session scan A 0dd0e2862ef4
seahorse-memory-system-audit is a skill published in the GitHub repository onceMisery/seahorse-agent (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,023 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 2026-08-30.
Other skills, from other repositories
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…
agents-md-revise
Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…