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.
/plugin marketplace add linkpranay-ai/context-engineering-protocolnpx agentmods add plugins/linkpranay-ai/context-engineering-protocol/claude-plugingit clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocolGrade A, and why
context-engineering-protocol 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 2d 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": "context-engineering-protocol",
"version": "0.5.0",
"description": "Source-cited, human-approved context packages (code graph + requirements + conventions) for AI coding agents -- assembled before a generation task runs, not guessed at afterward.",
"author": {
"name": "Pranay Mishra"
},
"homepage": "https://github.com/linkpranay-ai/context-engineering-protocol",
"repository": "https://github.com/linkpranay-ai/context-engineering-protocol",
"license": "Apache-2.0",
"keywords": [
"context-engineering",
"code-graph",
"requirements",
"human-approval"
]
}
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.
- 2d ago First seen · 18 lines scan A d36a592be4bd
context-engineering-protocol is a plugin published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed 2d 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
robrain
Plugin marketplace listing 1 plugin: robrain.
claude-code
Institutional memory for AI coding agents: deterministic decision capture and pre-task warnings about previously REJECTED approaches, backed by your self-hosted RoBrain stack.
breaking-coding-chaos
Human-in-the-loop dual-loop skills: throughline, plan-spar, clean-cut.
carryover
Carry your context across AI coding tools — shared memory, token compression, a leaner agent.
carryover
Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.
token-master
Plugin marketplace listing 1 plugin: token-master.