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 commands/wasintoh/toh-framework/toh-protectgit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote 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/commands/wasintoh/toh-framework/toh-protect)<a href="https://agentmods.dev/commands/wasintoh/toh-framework/toh-protect"><img src="https://agentmods.dev/badge/commands/wasintoh/toh-framework/toh-protect.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 | $0.00013 | $0.01728 |
| Opus 5 | $0.00006 | $0.00864 |
| Sonnet 5 | $0.00003 | $0.00346 |
| Haiku 4.5 | $0.00001 | $0.00173 |
Grade A, and why
toh-protect 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 5d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/toh-protect - Security Audit
Purpose
Comprehensive security audit for AI-generated code. Scans for vulnerabilities, hardcoded secrets, injection risks, and configuration issues before deployment.
Signature Command
/toh-protect [scope]
/toh-pt [scope]
/toh-security [scope]
/toh-audit [scope]
Workflow
User: /toh-protect
+-------------------------------------------------------------+
| SECURITY AUDIT |
+-------------------------------------------------------------+
| 0. READ MEMORY (Tiered - not all 7) |
| Tier 1 - read ALWAYS (~800 tokens): |
| |- .toh/memory/active.md (current task) |
| +- .toh/memory/summary.md (project overview) |
| Tier 2 - read per task type: |
| |- .toh/memory/changelog.md (session changes) |
| |- .toh/memory/components.md (existing components) |
| +- .toh/memory/architecture.md (project structure) |
| Tier 3 - only when referenced: |
| |- .toh/memory/decisions.md (past decisions) |
| +- .toh/memory/agents-log.md (agent activity) |
| |
| 1. READ Skills |
| +- ~/.toh/skills/security-engineer/SKILL.md |
| |
| 2. LEVEL 1: Quick Check |
| |- Hardcoded secrets |
| |- Dangerous code patterns |
| |- Basic auth issues |
| +- Obvious injection vectors |
| |
| 3. LEVEL 2: Deep Analysis |
| |- SQL/XSS/Command injection |
| |- Auth/Authorization flaws |
| |- AI-generated code risks |
| +- Configuration security |
| |
| 4. DEPENDENCY AUDIT |
| +- npm audit |
| |
| 5. SECURITY HEADERS CHECK |
| |- Content-Security-Policy |
| |- X-Frame-Options |
| |- HSTS, etc. |
| |
| 6. GENERATE REPORT |
| +- Save to .toh/security-audit-[date].md |
| |
| 7. SAVE MEMORY |
| |- Update active.md (ALWAYS - audit results) |
| |- Update summary.md (if shape changed) |
| +- Update decisions.md (security decisions) |
+-------------------------------------------------------------+
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.
- 5d ago First seen · 250 lines · 13 tokens per session scan A 28c900415014
toh-protect is a command published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 1,728 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
brainstorm
Command dispatcher for brainstorm.
start
Operate in Agentic Loop mode: create or refine the durable task record, route maintainer, engineer, and auditor roles, verify evidence, certify the finished work unit, and close out according to the project backend.
plan
Command dispatcher for plan.
planflow
Draft a plan and get it approved as an editable flowchart in the browser before executing.
hello
Trivial hello command from example. Used to verify plugin installation works end-to-end.
commands
Complete reference for all pair programming session commands.