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.
npx agentmods add instructions/iampantherr/securecontext/claude-mdgit clone --depth 1 https://github.com/iampantherr/SecureContextWrote 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/instructions/iampantherr/securecontext/claude-md)<a href="https://agentmods.dev/instructions/iampantherr/securecontext/claude-md"><img src="https://agentmods.dev/badge/instructions/iampantherr/securecontext/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01689 | $0.01689 |
| Opus 5 | $0.00844 | $0.00844 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
SecureContext CLAUDE.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SecureContext — Agent Instructions
What This Project Is
A fully auditable, open-source Claude Code MCP plugin that replaces context-mode.
Provides context-window optimization (sandbox execution, FTS5+vector knowledge base,
MemGPT-style persistent memory, session continuity, SSRF-protected web fetch) with
maximum security — no pre-compiled bundles, no credential leakage, no cloud sync.
Plugin ID: zc-ctx
Version: 0.22.5
License: MIT
Language: TypeScript (Node.js ≥ 22)
Directory Layout
SecureContext/
├── src/
│ ├── server.ts MCP server entrypoint — 13 tools
│ ├── config.ts All constants + env var overrides
│ ├── migrations.ts Versioned schema migrations (9 migrations)
│ ├── sandbox.ts Isolated code executor (python/js/bash)
│ ├── knowledge.ts Hybrid BM25+vector KB + cross-project search
│ ├── embedder.ts Ollama nomic-embed-text client
│ ├── memory.ts MemGPT working memory (agent namespacing)
│ ├── fetcher.ts 4-layer SSRF-protected URL fetcher
│ ├── integrity.ts SHA256 tamper detection
│ ├── session.ts JSONL event log reader
│ └── *.test.ts Vitest unit tests (248 tests)
├── hooks/
│ ├── pretooluse.mjs Blocks risky tool calls
│ ├── posttooluse.mjs Logs session metadata (read-only)
│ └── stop.mjs Session boundary marker
├── security-tests/
│ └── run-all.mjs 84 automated attack vectors
├── .github/workflows/ci.yml Build + unit tests + security tests on every push
├── .claude-plugin/
│ └── plugin.json Claude plugin manifest
├── install.mjs One-command installer (CLI + Desktop App)
├── ARCHITECTURE.md Full architecture reference
├── SECURITY_REPORT.md Threat model + security audit
├── CLAUDE.md THIS FILE
├── package.json
├── package-lock.json Always committed — locked deps
└── tsconfig.json
Build Commands
npm ci # Install deps from lockfile
npm run build # tsc compile → dist/
npm test # Vitest unit tests (248 tests)
node security-tests/run-all.mjs # 84 security attack vectors
node install.mjs # Install for Claude Code CLI + Desktop App
node install.mjs --uninstall # Remove from all configs
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.
- 3d ago First seen · 145 lines · 1,689 tokens per session scan A 1dff92a23d4f
SecureContext CLAUDE.md is an instructions file published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 4d ago), licensed MIT. It adds 1,689 tokens to every session, about $0.0084 per session on Opus 5. 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 instructions, from other repositories
ClawMem AGENTS.md
Instructions for yoloshii/ClawMem, covering clawmem — agent quick reference, inference at a glance, install, or step by step and memory retrieval (90/10 rule).
pine-of-glass AGENTS.md
Instructions for tmustier/pine-of-glass, covering pine-of-glass: agent notes, commands, layout & rules, style and releasing.
ClawMem CLAUDE.md
Instructions for yoloshii/ClawMem: Claude Code reads CLAUDE.md natively (not AGENTS.md), so this file imports the root SSOT.
Bilinc AGENTS.md
AGENTS.md instructions for atakanelik34/Bilinc, covering bilinc agent operating contract, stack lock, repo commands, scope discipline and approval gates.
moss AGENTS.md
Instructions for usemoss/moss, covering agents.md, what this repo is, repository layout, integrations & cookbooks and framework cookbooks (examples/cookbook/).
Tianshu-harness CLAUDE.md
Instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.