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 skills add ayushcodes10/echo-mem --skill v3-security-overhaulgit clone --depth 1 https://github.com/ayushcodes10/echo-memWrote 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/skills/ayushcodes10/echo-mem/v3-security-overhaul)<a href="https://agentmods.dev/skills/ayushcodes10/echo-mem/v3-security-overhaul"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-security-overhaul/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/skills/ayushcodes10/echo-mem/v3-security-overhaul"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-security-overhaul.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00052 | $0.00591 |
| Opus 5.5 | $0.00021 | $0.00236 |
| Sonnet 5.5 | $0.00010 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
V3 Security Overhaul scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execFile } from 'child_process'; This is a copy
100% identical to V3 Security Overhaul — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
V3 Security Overhaul
What This Skill Does
Orchestrates comprehensive security overhaul for Codex-flow v3, addressing critical vulnerabilities and establishing security-first development practices using specialized v3 security agents.
Quick Start
# Initialize V3 security domain (parallel)
Task("Security architecture", "Design v3 threat model and security boundaries", "v3-security-architect")
Task("CVE remediation", "Fix CVE-1, CVE-2, CVE-3 critical vulnerabilities", "security-auditor")
Task("Security testing", "Implement TDD London School security framework", "test-architect")
Critical Security Fixes
CVE-1: Vulnerable Dependencies
npm update @anthropic-ai/Codex@^2.0.31
npm audit --audit-level high
CVE-2: Weak Password Hashing
// ❌ Old: SHA-256 with hardcoded salt
const hash = crypto.createHash('sha256').update(password + salt).digest('hex');
// ✅ New: bcrypt with 12 rounds
import bcrypt from 'bcrypt';
const hash = await bcrypt.hash(password, 12);
CVE-3: Hardcoded Credentials
// ✅ Generate secure random credentials
const apiKey = crypto.randomBytes(32).toString('hex');
Security Patterns
Input Validation (Zod)
import { z } from 'zod';
const TaskSchema = z.object({
taskId: z.string().uuid(),
content: z.string().max(10000),
agentType: z.enum(['security', 'core', 'integration'])
});
Path Sanitization
function securePath(userPath: string, allowedPrefix: string): string {
const resolved = path.resolve(allowedPrefix, userPath);
if (!resolved.startsWith(path.resolve(allowedPrefix))) {
throw new SecurityError('Path traversal detected');
}
return resolved;
}
Safe Command Execution
import { execFile } from 'child_process';
// ✅ Safe: No shell interpretation
const { stdout } = await execFile('git', [userInput], { shell: false });
Success Metrics
- Security Score: 90/100 (npm audit + custom scans)
- CVE Resolution: 100% of critical vulnerabilities fixed
- Test Coverage: >95% security-critical code
- Implementation: All secure patterns documented and tested
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.
- 1mo ago Changed 118be5060cae
- 1mo ago First seen · 82 lines · 52 tokens per session scan A 4123b78d5a2d
V3 Security Overhaul is a skill published in the GitHub repository ayushcodes10/echo-mem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 591 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to V3 Security Overhaul, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
tdd-with-memory
A test-first implementation workflow that recalls past decisions, conventions, and lessons before coding. TDD, or test-driven development, means writing a failing test first, then implementing the code and finally cleaning it up.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
taste
Use when implementing any feature, bugfix, or behavior change, before writing the implementation code. Especially use under pressure - production is down, "just make it work", "quick fix" - which is when it gets skipped.
memmesh-integrate
Integrate MemMesh into an existing repository using a goal-driven, test-first (TDD) pipeline. Detects the repo's language/stack, asks whether to use MemMesh Hosted (SDK, managed) or Local (CLI + MCP over SQLite), writes failing tests before any implementation, and lands additive, feature-flag-gated code that a…
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.