G6daddy
Developer tools · from Mythos Machine

Put a guard at every gate.

Open-source tools that stand between your coding agents and the expensive mistakes: unapproved specs, poisoned MCP servers, forgotten decisions, rm -rf, runaway token bills and dirty ERP data. MIT-licensed cores that run on your machine. Pro add-ons are $11, one time.

Janus of Agents

Sign-off gate · traceability · npm

From approved spec to tested code, with proof. No sign-off, no plan. No passing test, no green gate.

  • Human sign-off records who approved and a SHA-256 hash of the spec. Edit the spec and the sign-off goes stale.
  • Tag tests with @req ids. check reads your JUnit XML and fails if a requirement has no test or a tagged test failed.
  • Drift detection names requirements changed since sign-off, with a line diff. OpenSpec and Superpowers compatible.
npm install -g @kurtfrancisco/janus
GitHub →Free · MIT · Node ≥ 20

Argus of MCP

Supply-chain scanner · npm

A hundred eyes on every MCP server and agent skill you install, before you trust a copied npx -y.

  • Finds MCP configs and skill folders for Claude, Cursor, VS Code and Windsurf, then runs offline static checks.
  • Flags hidden prompt injection, invisible Unicode, dangerous commands, credential paths, unpinned packages and hardcoded secrets (values always masked).
  • Text, JSON, SARIF and HTML reports with CI-friendly exit codes. Status per the README: MVP, static, pattern-based analysis.
npx @kurtfrancisco/argus scan
GitHub →Free · MIT · Node ≥ 18

Alethea of Agents

Decision memory · npm

Your agent forgets what was decided last month. Alethea makes it remember.

  • Stores ADR-style decisions and machine-checkable constraints as markdown in your repo's .decisions/ folder.
  • check_conflicts tests a proposed change against forbid / require / forbid-path rules. The CLI exits 1 on a violation.
  • Local stdio MCP server and CLI. Records link to Janus requirement ids, tests and commits.
npm install -g @kurtfrancisco/alethea
GitHub →Free · MIT · Node ≥ 20

Talos of Humans

Runtime guardrails · npm · Pro

A bronze guard at the edge of your shell. Dangerous agent actions get blocked before they run.

  • Five free guards: destructive commands, secrets written to files, exfiltration, force-push to main, and edits outside the project root.
  • talos init writes the hook config for Claude Code, Cursor and Codex. Deterministic, no LLM calls.
  • Pro adds extra guards, strict / ci profiles, a hash-chained audit log and an HTML report. Honest limit from the README: it's a guardrail, not a sandbox.
npx @kurtfrancisco/talos init --agent all

Hephaestus of Skills

Skill forge · GitHub · Pro

Forge an Agent Skill a stranger can install, and pay for.

  • Lints a skill against the Agent Skills spec and flags descriptions that won't trigger.
  • Builds every install format: skill folder, claude.ai upload zip, Claude Code plugin and a checksummed release zip.
  • Pro adds per-buyer watermarking, leak tracing and sales-page drafts. Python 3.8+, standard library only.
git clone https://github.com/fpavia111-creator/hephaestus cd hephaestus && ./install.sh claude

Leonidas of the Web

Compliance-first outbound · npm · Pro

Let your agent research and draft cold email. Leonidas holds the line: nothing goes out without a human.

  • Never auto-sends. Draft mode is the default, and only a human approves unless you change that setting yourself.
  • CAN-SPAM gate: postal-address footer, opt-out line, List-Unsubscribe headers, and fake Re: subjects blocked on first touch.
  • Daily and per-domain caps, warmup ramp, bounce-rate breaker and a hash-chained audit log. Based on Harvey by Ethan Rogers (MIT); not affiliated. Not legal advice.
npx -y @kurtfrancisco/leonidas init --icp home_services

Codex on Adderall

Plan → build → review · npm · Pro

One model plans, another builds, a lead reviews, and a hard stop before the bill gets ugly.

  • Spec gate: no handoff until the spec has a goal, acceptance criteria, scope, a test plan and named files.
  • Hard USD and token budgets per run and per day. A preflight estimate stops a call before it crosses a limit.
  • The server never edits files, runs git or deletes anything. Based on Codex on Crack by Ethan Rogers (MIT). Not affiliated with Ethan Rogers or OpenAI.
claude mcp add codex-on-adderall -- npx -y @kurtfrancisco/codex-on-adderall mcp

Olympus ERP

ERP migration toolkit · Python · MIT

Find the import-breaking data before go-live finds it for you. A local workspace for ERP data migrations, for example QuickBooks to NetSuite.

  • Hermes reads CSV/XLSX exports, suggests column mappings and runs deterministic checks: required fields, duplicate IDs, broken references, unbalanced journals.
  • Themis ties human sign-off to the mapping spec's SHA-256. Poseidon compares a source export with a trial-load export.
  • Zeus is a conservative go-live gate that never outputs GO. Not a complete ERP, hosted SaaS or certified vendor connector.
git clone https://github.com/fpavia111-creator/olympus-erp cd olympus-erp python -m venv .venv && . .venv/bin/activate python -m pip install -e ".[pdf]" olympus web --workspace . --port 8765
GitHub →Free · MIT · Python 3.11+
Stronger together

One gate is good. A chain is a system.

Codex on Adderall loads Janus, Argus and Talos when they are installed. Alethea links its decisions to Janus requirement ids. Integrations are optional.

01

Agree · Janus

The run is blocked until the spec validates and a human has signed it off.

02

Remember · Alethea

Past decisions and constraints come back as context before the agent starts.

03

Vet · Argus

Worker tools are checked for injection and exfiltration patterns first.

04

Guard · Talos

A deny blocks a CLI worker's command, even when destructive actions are allowed.

For consultants & mid-market teams

The Migration Integrity Scan

Bring a migration. We run Hermes and Poseidon on your exports with you and walk through every finding, so the problems surface in a review instead of in a trial load.

Free demo$0

A walkthrough of the full workflow on the built-in fictional demo data. No real data needed.

Scoped readiness review$499–$1,500

Diagnose and map your exports, with rejects, change logs and a findings report.

Trial-load assurance$1,500–$5,000

Reconcile source against trial-load exports and assemble the evidence pack.

Priced by scope (objects, files, rounds, environment). Data-handling terms are agreed before any real data is shared. Ranges are estimates, not quotes.

Book the free demo