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/kadiresen/context-bankWrote 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/kadiresen/context-bank/plugin)<a href="https://agentmods.dev/plugins/kadiresen/context-bank/plugin"><img src="https://agentmods.dev/badge/plugins/kadiresen/context-bank/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/kadiresen/context-bank/plugin"><img src="https://agentmods.dev/badge/plugins/kadiresen/context-bank/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
context-bank 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": "context-bank",
"displayName": "Context Bank",
"version": "3.0.3",
"description": "Keep AI project memory small, in git, and shared across tools. Teaches Claude the retrieval-first .ai/ contract, checks bank health at session start, and adds doctor, compact and init commands.",
"author": {
"name": "Kadir Esen",
"url": "https://github.com/kadiresen"
},
"homepage": "https://github.com/kadiresen/context-bank#readme",
"repository": "https://github.com/kadiresen/context-bank",
"license": "MIT",
"keywords": [
"memory-bank",
"context-engineering",
"agents-md",
"ai-memory",
"project-context"
]
}
What it installs
The manifest is a name and a version. 4 skills, 1 hook travel with it, and installing the plugin installs all of them — 158 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- yesterday Changed 84d72732c2c7
- 2d ago Changed 80222b872b1d
- 14d ago First seen · 21 lines scan A ec8126eeb952
context-bank is a plugin published in the GitHub repository kadiresen/context-bank (9 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 2026-09-27.
Other plugins, from other repositories
memseek-memory
Durable, provenance-aware project memory for Claude Code.
atomicmemory
Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.
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.
prime-context
Self-learning project context — bare /prime-context captures the session's learnings into area context files; /prime-context loads context on demand; thin AGENTS.md router, structure audit (doctor), drift warnings at session start.
wire-memory
Persistent memory for AI agents. Connect to a Wire container to remember decisions, patterns, and context across sessions.
governed-context
Governed memory (explicit states, fail-closed sensitivity gates, quarantine-only writes) as a dependency-free MCP server, plus a blind-evaluation protocol skill for honest A/B comparisons.