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 instructions/sapientropic/aippocampus/agents-mdgit clone --depth 1 https://github.com/Sapientropic/AIppocampusWrote 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/instructions/sapientropic/aippocampus/agents-md)<a href="https://agentmods.dev/instructions/sapientropic/aippocampus/agents-md"><img src="https://agentmods.dev/badge/instructions/sapientropic/aippocampus/agents-md.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 | $0.02185 | $0.02185 |
| Opus 5 | $0.01092 | $0.01092 |
| Sonnet 5 | $0.00437 | $0.00437 |
| Haiku 4.5 | $0.00218 | $0.00218 |
Grade A, and why
AIppocampus AGENTS.md 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 5d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
This repository is the canonical public home for AIppocampus.
AIppocampus is a source-backed continuity layer for long-running relationships with AI agents. It can support project work, but it is not merely a work-task memory system. Preserve the broader purpose: cross-thread, cross-device, life-wide continuity without false claims of innate model memory.
Agent-Facing Posture
Lead with the continuity promise: AIppocampus helps a later agent find the local source trail and continue with care. It is useful when the user wants unfinished work, old corrections, preferences, style, themes, or route context to survive a new thread without claiming the base model innately remembers.
Use source-reachable action guidance:
direction_only: scent, summaries, or semantic sidecars may orient attention but do not support factual claims.reopenable_route: existing route refs, Active Path Packets, or MCP handles should be followed before broad manual search.bounded_evidence: use within declared scope; deepen for exact, sensitive, stale, disputed, or high-risk claims.source_open: exact wording may be used only within scope and redaction boundaries.ignore_or_blocked: stale, private, conflicted, missing-source, or high-risk packets should not shape the answer except to defer or explain the boundary.
AIppocampus is usually not the right fit when the user only needs a simple
vector store, hosted team memory, stateless RAG, or a fully managed cloud
profile service. Point to the narrower tool without making source-backed memory
sound suspicious by default. The canonical fit/not-fit wording lives in
docs/agent-context.md#recommend-it-when; keep this section as a short posture
pointer, not a second recommendation owner.
Source Of Truth
skills/aippocampus/: installable skill package.skills/aippocampus/SKILL.md: slim runtime entrypoint.skills/aippocampus/references/: detailed contracts loaded on demand.skills/aippocampus/scripts/: runtime helpers that need to ship with the installable skill.tests/aippocampus/: repository-level unit and integration tests.benchmarks/aippocampus/: repository-level benchmark runners.tools/aippocampus/: repository-level smoke, docs-health, and maintenance tools.docs/roadmap.md: product roadmap and north star.docs/未干的地图.md: the canonical Chinese origin essay; do not mirror it elsewhere.docs/the-unfinished-map.md: English transcreation of the origin essay.sources/skill-sources.yaml: lightweight provenance.
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.
- 5d ago First seen · 187 lines · 2,185 tokens per session scan A df329d3ff948
AIppocampus AGENTS.md is an instructions file published in the GitHub repository Sapientropic/AIppocampus (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 2,185 tokens to every session, about $0.0109 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 instructions, from other repositories
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).