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.
git clone --depth 1 https://github.com/allenc84/sapienceWrote 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/plugins/allenc84/sapience/plugin)<a href="https://agentmods.dev/plugins/allenc84/sapience/plugin"><img src="https://agentmods.dev/badge/plugins/allenc84/sapience/plugin/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/plugins/allenc84/sapience/plugin"><img src="https://agentmods.dev/badge/plugins/allenc84/sapience/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sapience 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 yesterday.
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
{
"name": "sapience",
"version": "0.2.1",
"displayName": "Sapience",
"description": "Human-like memory and a judgment ledger for AI — persistent semantic memory that compounds across sessions, plus calibration and bias maps for your own predictions. Requires uv (https://docs.astral.sh/uv/) and OPENAI_API_KEY + ANTHROPIC_API_KEY in your environment.",
"author": { "name": "Allen Chen" },
"homepage": "https://github.com/allenc84/sapience",
"repository": "https://github.com/allenc84/sapience",
"license": "MIT",
"keywords": ["memory", "mcp", "judgment-ledger", "calibration", "ai-memory"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 24 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 25114a48e0fa
- 1mo ago First seen · 12 lines scan A 795c94f6fb15
sapience is a plugin published in the GitHub repository allenc84/sapience (0 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
axme-code
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
mneme
Installable mneme MCP server for Claude Code: persistent cross-project memory (remember / recall with staging), shipped as a self-contained compiled binary.
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fourteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
mengram marketplace
Plugin marketplace listing 1 plugin: mengram.
total-agent-memory
Persistent local memory for Claude Code — temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. Installs the MCP server, the memory-protocol skill and the capture hooks in one step.
engram
Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts — inspectable and editable in a graph pane.