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 T4LEL/Claude-Arsenal --skill hardengit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/harden)<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/harden"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/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/skills/t4lel/claude-arsenal/harden"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/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 | $0.00041 | $0.00749 |
| Opus 5.5 | $0.00016 | $0.00300 |
| Sonnet 5.5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
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 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.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harden
A defensive security pass, deeper than the /ship-it deploy gate. Run before real users, payments, or sensitive data.
Copy this checklist and check off items as you complete them:
Harden Progress:
- [ ] Step 1: Audit
- [ ] Step 2: Triage
- [ ] Step 3: Fix
- [ ] Step 4: Verify (mandatory)
- [ ] Step 5: Record
- [ ] Report
Step 1 — Audit
Delegate to the security-auditor agent with a full pass over: auth flows, RLS/access control, input validation, secret handling, security headers, rate limiting, dependency audit. On Supabase, also run the supabase MCP get_advisors tool and fold its output into the same findings list. If any current-library security guidance is needed (auth library config, header middleware, CSP syntax), fetch it via the context7 MCP tools rather than relying on memory. Secrets encountered during the audit stay in env vars and are never printed into chat, code, logs, or commits.
Step 2 — Triage
Every finding gets a severity — Critical / High / Medium / Low — and a concrete exploit scenario: who, what request, what they get. A finding without an exploit scenario is not triaged yet; send it back to the security-auditor agent for specifics rather than guessing at a severity. Any severity or count you can't verify from real output is an unverified assumption — label it, don't state it as fact.
Step 3 — Fix
Criticals and Highs get fixed now. Route each to the right builder agent as one bounded task per fix: schema/RLS/policy issues to the db-designer agent, application-level issues (auth checks, input validation, headers, rate limiting) to the backend-builder agent, and dependency vulnerabilities to the backend-builder agent for patch/minor bumps or the refactor-engineer agent when the fix requires a major upgrade. Don't batch unrelated fixes into one task — each fix needs its own verification in Step 4. Never commit, push, deploy, or publish fixes without the user's explicit ask.
Step 4 — Verify (mandatory)
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 First seen · 48 lines · 41 tokens per session scan A 43a9a77f29e5
harden is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 749 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list with only publicly listed, source-cited contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…