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/maxbaluev/accreted-intelligenceWrote 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/maxbaluev/accreted-intelligence/claude)<a href="https://agentmods.dev/plugins/maxbaluev/accreted-intelligence/claude"><img src="https://agentmods.dev/badge/plugins/maxbaluev/accreted-intelligence/claude/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/maxbaluev/accreted-intelligence/claude"><img src="https://agentmods.dev/badge/plugins/maxbaluev/accreted-intelligence/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
acc 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 1mo 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
{
"name": "acc",
"version": "0.1.0",
"_version_note": "Baseline 0.1.0 == Cargo.toml at first public release. The plugin version is loosely coupled to the engine version: it bumps independently, and may diverge from the engine, only when the plugin's hook/MCP surface (manifest, hook mappings, skills) changes on its own.",
"description": "scored-memory loop — two verbs (acc_retrieve + acc_act) + lifecycle hooks"
}
What it installs
The manifest is a name and a version. 3 skills, 8 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 83 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill solve A 28 tokens
- Skill commitments A 26 tokens
- Skill frames A 29 tokens
- Hook PostToolUse A not measured
- Hook SessionStart A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
- Hook PreCompact A not measured
- Hook SessionEnd A not measured
- Hook Stop A not measured
- MCP server acc A not measured
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.
- 1mo ago First seen · 7 lines scan A dddb56223c13
acc is a plugin published in the GitHub repository maxbaluev/accreted-intelligence (7 stars, last pushed 3mo ago), licensed Apache-2.0. 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
hippo-memory
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
plur
Persistent, local-first shared memory for AI agents. Corrections, preferences, and conventions persist across sessions, tools, and machines — stored as plain YAML on your disk, with zero-cost local search.
palinode
Persistent memory for AI agents. Git-versioned markdown files as source of truth, hybrid SQLite-vec + FTS5 search, deterministic compaction. Every line in your agent's brain has a git blame.
yantrikdb
Cognitive memory for AI agents — semantic recall, a knowledge graph, contradiction detection and procedural learning. Local-first: one SQLite file, no account, no telemetry.
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
mnemos-memory
Biomimetic long-term memory for Claude Code with surprisal gating, mutable reconsolidation, affective routing, and sleep consolidation.