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.
git clone --depth 1 https://github.com/obiwancenobi/klambenWrote 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/obiwancenobi/klamben/harden)<a href="https://agentmods.dev/commands/obiwancenobi/klamben/harden"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/harden/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/commands/obiwancenobi/klamben/harden"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/harden.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 | $0.00024 | $0.00426 |
| Opus 5 | $0.00012 | $0.00213 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
harden 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 10d 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
/harden
Prep a screen for production. Add the safety scaffolding most AI- generated code misses.
When to use
- Taking a prototype to production
- After
/auditshows errors in code-quality category - Before a real-user launch
Actions
- Check design context: If
.klamben.mdexists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below. - Loading states: Any async button/action gets a
_loadingflag and disabled-while-loading UI - Error states: Wrap async calls in try/catch; show user-facing
error (SnackBar or inline); log to
debugPrint - Empty states: Any list screen gets a meaningful empty state
- Mounted guards: Every
setStateorcontextuse afterawaitgetsif (!mounted) return; - Dispose: Every
*Controllerfield inStategets disposed indispose() - Null safety:
!→ explicit null check where possible - Swallowed errors: Empty
catch (_)→ logged + reported
Output
harden lib/screens/home.dart
+ late bool _loading = false;
+ try/catch around api.save() with user-facing SnackBar on error
+ if (!mounted) return; guards on 3 async methods
+ @override void dispose() { _controller.dispose(); super.dispose(); }
+ Empty state widget when items.isEmpty
8 safety additions.
Run tests before committing.
Do NOT
- Change business logic
- Add features the user didn't ask for
- Touch unrelated screens
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.
- 10d ago First seen · 57 lines · 24 tokens per session scan A 945c4da8ff14
harden is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 426 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 2026-08-31.
Other commands, from other repositories
design-solution
Turn an approved PRD or implementation goal into SRS/FRS technical requirements (How), architecture, contracts, and verification decisions.
domino-app-init
Initialize a new Domino-ready web application with Vite+React, Streamlit, Dash, or Flask. Configures proxy-compatible settings and app.sh.
scaffold-fullstack
Initialize a new fullstack Go + React project with standard directory structure, configs, and Docker Compose.
create-ai-app
Create a Full Stack AI application with FastAPI backend and React + ShadCN frontend.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.