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/zealynxsecurity/krait/krait-initgit clone --depth 1 https://github.com/ZealynxSecurity/kraitWhat 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 | $0.00000 | $0.00347 |
| Opus 5 | $0.00000 | $0.00173 |
| Sonnet 5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
krait-init 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.
What it actually says
Krait Init — Project Readiness Check
Standalone readiness check before running /krait. Verifies tools, project shape, gitignore, MCP wiring, and ~/.claude install. Reports what's missing — does NOT install or modify anything.
Use this when you want to validate your environment without committing to a full audit run (CI setup, debugging, "is my env ready?"). /krait runs the hard checks automatically on every invocation, so most users will never need to call this directly.
Usage
/krait-init
/krait-init src/contracts/ # check a specific subdir
Instructions
Read and follow ~/.claude/skills/krait/preflight/instructions.md in report mode.
That skill defines every check, the hard-vs-soft distinction, and the output table format. Your job is to run all of its checks (hard + soft, including ~/.claude skills sync) and emit the full summary table with a single-line verdict at the end.
CRITICAL:
- Read-only. Do NOT install dependencies, modify
.gitignore, edit.mcp.json, or write.audit/*files unless the user explicitly says "go ahead" / "fix it" / "yes". - For environmental misses (e.g.
forgenot on PATH), propose the install command but don't run it yourself. - Do all checks in parallel where possible. A tight pass/fail table beats narration.
If the verdict is READY or READY (warnings), suggest /krait next. If it is NOT READY, do not suggest /krait — fix the env first.
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 · 26 lines · 0 tokens per session scan A 39740aaffd16
krait-init is a command published in the GitHub repository ZealynxSecurity/krait (22 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 347 tokens. 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
dashboard
Open the ChainGPT marketplace dashboard (localhost web UI — Overview, Skills, Activity, Health, About).
deploy
Deploy Suwappu services on Railway. Usage: /deploy [prod|dev] [python-api|python-worker|terminal|api-ts|showcase|all].
status
Check what's actually running: Railway control plane + deep health + logs + CI. Usage: /status [prod|dev] [--quick].
audit
Attacker-minded security audit of scoped files. Traces auth + money-path data flows, streams compact findings incrementally (never one giant end-of-session JSON dump). Usage: /audit [attack-class].
audit-deps
Audit third-party dependencies — resolve installed versions, cross-reference known-vulnerable releases, and flag vendored code that has diverged from upstream.
pre-deploy
Interactive pre-launch security checklist — walk the operational and code-safety gates and produce a final GO / NO-GO with each item PASS / FAIL / N-A.