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/Kin9Zeus/senior-engineer-skillsWrote 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/kin9zeus/senior-engineer-skills/snr-harden)<a href="https://agentmods.dev/commands/kin9zeus/senior-engineer-skills/snr-harden"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-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/kin9zeus/senior-engineer-skills/snr-harden"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-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 | $0.00841 |
| Opus 5 | $0.00012 | $0.00420 |
| Sonnet 5 | $0.00005 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
snr-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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Hardening Pass
Harden: $ARGUMENTS (default: the whole repository).
Load the security-hardening skill. Defensive security only — never scan,
probe or send traffic to infrastructure the user has not confirmed they own or
are authorised to test.
Order of work — top-down by real-world yield
1 Secrets — anything committed is compromised. Start here
2 Access control — the highest-severity findings live here
3 Injection — SQL, command, template, path, deserialization
4 Authentication — sessions, tokens, resets, MFA, rate limits
5 XSS and CSP
6 SSRF, CSRF, CORS, redirects, uploads
7 Configuration — debug mode, headers, exposed endpoints
8 Supply chain — dependencies, install scripts, CI
9 Crypto — hashing, randomness, JWT verification
10 Logging — auth events logged; no secrets or PII in logs
Run the scan first
skills/security-hardening/scripts/secret-scan.sh (or .ps1). It is read-only.
Everything it reports is a lead, not a finding — confirm each by reading the
file.
The two checks that find the most severe issues
1 · Secrets in git history. Anything ever committed is disclosed, in every clone and fork. Remediation order is fixed and non-negotiable:
1. ROTATE the credential — immediately, before anything else
2. Check the provider's audit log for abuse
3. Purge the history (git filter-repo / BFG), everyone re-clones
4. Enable secret scanning and a pre-commit hook
Purging without rotating leaves the key live and makes the repository look clean. That is the most common mistake in this whole area.
2 · Object-level authorization. Authenticate as user A; request user B's
resource by changing an identifier. A 200 is a P0. Grep for the shape:
grep -rEn 'findById|findByPk|findOne\(\{ *_?id|\.get\(pk=|WHERE id *=' \
--exclude-dir={node_modules,.git,vendor,dist} . | head -30
Then read each hit and ask: where is the caller's relationship to this object
asserted? Grep for the mitigating control before declaring a finding — a false
P0 costs the reader's trust for the whole report.
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.
- 11d ago First seen · 90 lines · 24 tokens per session scan A b98bc4ac0580
snr-harden is a command published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 841 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
scaffold-project
Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
gate
Run the one-command quality gate and report the real N/N result. Use before claiming any build/review is done.
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
code-review
OWASP-mapped, skill-aware code review with autofix suggestions. Reviews the diff, not the world.
adr
Write an architecture decision record as Markdown in the user's repository. Use when invoked as /document-design-system:adr. Produce designed HTML or PDF only when asked.