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 ictechgy/context-guardnpx agentmods add plugins/ictechgy/context-guard/marketplacegit clone --depth 1 https://github.com/ictechgy/context-guardGrade A, and why
context-guard 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "context-guard",
"description": "Marketplace for ContextGuard: Claude Code context hygiene, token/cost visibility, and local guardrails.",
"owner": {
"name": "jinhongan"
},
"plugins": [
{
"name": "context-guard",
"source": "./plugins/context-guard",
"description": "ContextGuard keeps AI coding-agent context lean, safe, and auditable with project-local setup, scans, large-read guards, output trimming/sanitizing, queryable log artifacts, budgeted context packs, tool/MCP schema pruning, statusline visibility, and usage audits.",
"license": "Apache-2.0",
"keywords": [
"context-safety",
"context-hygiene",
"context-guard",
"claude-code",
"tokens",
"cost",
"context",
"settings",
"diet",
"read-symbol",
"large-read-guard",
"hooks",
"sanitize-output",
"grep-sanitizer",
"diff-sanitizer",
"secret-redaction",
"setup-wizard",
"interactive-setup",
"artifact-escrow",
"context-escrow",
"queryable-logs",
"tool-schema",
"mcp",
"schema-pruning",
"context-pack",
"research-radar",
"experimental-roadmap",
"gated-experiments",
"future-roadmap"
],
"category": "developer-tools",
"tags": [
"context-safety",
"context-hygiene",
"context-guard",
"token-optimization",
"cost-management",
"context-management",
"settings-scanner",
"read-guard",
"output-sanitizer",
"secret-redaction",
"setup-wizard",
"interactive-setup",
"artifact-escrow",
"context-escrow",
"queryable-logs",
"tool-schema",
"mcp",
"schema-pruning",
"context-pack",
"research-radar",
"experimental-roadmap",
"gated-experiments",
"future-roadmap"
],
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 First seen · 74 lines scan A 293bdeadf6e3
context-guard is a plugin published in the GitHub repository ictechgy/context-guard (3 stars, last pushed yesterday), 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
chanmeng-audio-hooks
Plugin marketplace listing 1 plugin: audio-hooks.
audio-hooks
Audio notifications + AI-controlled config for Claude Code, Cursor IDE, and Codex CLI events. 39 hook events + 44 matcher variants, each with its own sound. Desktop toasts without a terminal, TTS, webhooks, status line + per-subagent rows, rate-limit alerts. Auto-bridges to Cursor IDE 3.2.16+; native install via…
fable-orchestrator
Fable 5-first multi-agent orchestration for Claude Code: a token-frugal chair profile with tier routing (Sonnet 5 carries the volume, Opus 5 the hard slices), chair-sized effort per worker, a Requirements Ledger, guard hooks that enforce the discipline, and automatic teammate reaping. A clarification phase grills an…
orchestrator
Token-frugal multi-agent orchestration for Claude Code, built for a Claude Fable 5 chair: Fable plans and decides, Sonnet 5 carries the volume, Opus 5 takes the hard slices and escalations — each worker's effort sized by the chair — and a two-tier verification valve guards the close. When the Fable limit runs dry, an…
ballast
Builds up to a goal in a field you have no expertise in — learns the foundations it needs and keeps every solved path for the next goal.
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.