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 receptron/mulmoterminal --skill securitygit clone --depth 1 https://github.com/receptron/mulmoterminalWrote 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/receptron/mulmoterminal/security)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/security"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/security/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/receptron/mulmoterminal/security"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/security.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 | $0.00036 | $0.01176 |
| Opus 5.5 | $0.00014 | $0.00470 |
| Sonnet 5.5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
blueprint-cloudflare-security 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 25d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security review
The app is built and runs. Before it is published, review it the way an attacker would read it, fix what is exploitable, and leave a report the person can read. The check does not take your word for it: it starts the Worker with wrangler dev and sends it the requests an attack would send.
Method
- Context. Read
.blueprint/spec.md(above all "必ず詰める点"), thensrc/worker/,src/client/,wrangler.jsonc,public/_headersandpackage.json. Note who may do what, where input enters, what is stored. - Audit, category by category (the list below). For each place input enters, trace it to where it is used.
- Fix every HIGH and MEDIUM finding, and add a test to
test/security.test.tsthat fails without the fix. - Report in
.blueprint/security-review.md(format below).
Severity: HIGH is directly exploitable (read or change someone's data, bypass sign-in, run code). MEDIUM needs a specific condition but the impact is real. LOW is defence in depth. Report a finding only when you can state how it is exploited and you are at least 70% sure. Do not report denial of service, rate limits, or missing validation on a field that cannot cause harm.
What to look at in this app (OWASP Top 10:2025)
- A01 Broken Access Control — the app is public: every
/apiroute enforces the spec's sign-in and roles in the Worker; with accounts, a row is read or changed only by whoever may. - A02 Security Misconfiguration — security headers on every response: the Worker's for
/api/*, andpublic/_headersfor the static files, which never go through the Worker; no permissive CORS. - A03 Software Supply Chain Failures —
yarn audit --groups dependencieshas no high or critical. - A04 Cryptographic Failures — passwords as salted PBKDF2 (Web Crypto), compared in constant time; secrets as
wrangler secrets, and
.dev.vars(and any.env) listed in.gitignore; cookiesHttpOnly,Secure,SameSite=Lax. - A05 Injection — SQL only with bound parameters; the screen never renders input as HTML.
- A06 Insecure Design — the spec's rules are enforced in the Worker, not only on the screen.
- A07 Authentication Failures — a new session at sign-in; sign-out ends it; no default password in the code.
- A08 Software or Data Integrity Failures — nothing from a request picks code to run; an uploaded file is checked for type and size.
- A09 Security Logging and Alerting Failures — sign-in failures and changes to data are logged (
console.logreacheswrangler tail), without passwords, cookies or secrets. - A10 Mishandling of Exceptional Conditions — every error reaches one handler that answers JSON without a stack; a failed check refuses rather than lets through.
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.
- 25d ago First seen · 77 lines · 36 tokens per session scan A 365cac0a37c6
blueprint-cloudflare-security is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,176 once invoked, about $0.0001 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 2026-09-30.
Other skills, from other repositories
ralph
Self-referential loop until task completion with configurable verification reviewer.
tdd
Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference.
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.
tdd
Build this test-first, one behavior at a time: $ARGUMENTS.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-workflow-testing
Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.