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 skills/sergeyizmailov/knowledge-delta-skills/secure-codingnpx skills add sergeyizmailov/knowledge-delta-skills --skill secure-codinggit clone --depth 1 https://github.com/sergeyizmailov/knowledge-delta-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/skills/sergeyizmailov/knowledge-delta-skills/secure-coding)<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/secure-coding"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/secure-coding.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.01923 |
| Opus 5 | $0.00030 | $0.00962 |
| Sonnet 5 | $0.00012 | $0.00385 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
secure-coding scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `fetch(userUrl)` without validation | SSRF | Internal scan, cloud metadata | How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure Coding (JS / Node.js / HTML / CSS)
Apply automatically when writing any web code — hardened by default. Validate deployment topology (reverse proxy, TLS termination, CDN) before applying trust proxy, HSTS preload, or cross-origin isolation defaults. AI-generated code has 2.74x more vulnerabilities than human-written; 45% of AI samples introduce an OWASP Top 10 vuln (Veracode, 100+ LLMs).
Workflow
New code: secure defaults first (helmet, cors explicit origins, rate-limit, body size limit) → per endpoint: auth middleware → zod validation → parameterized queries → generic errors → scan against "Never Do" table.
Dependencies (prefer context7 MCP; else npm registry / GitHub / GHSA): latest stable version, no open critical/high CVEs, maintainer disqualify only on: deprecated, archived, unanswered CVE > 90 days, ownership transferred to unknown party (mature libs like argon2/helmet/jose sit quiet for months and stay canonical). Apps: package-lock.json + npm ci; libs: semver ranges + audit in CI. Prefer Safe Library Stack below.
Auditing existing code: entry point → routes → middleware chain → static serving → npm audit + pinned versions + known compromised packages → configs (NODE_ENV, exposed .env/.git/source maps, debug endpoints) → per route: auth → validation → data handling → errors → headers/CSP/CORS/cookies/ports → report.
Audit output format:
### [CRITICAL/HIGH/MEDIUM/LOW] Finding title
- **Location**: file:line
- **Vulnerability**: CWE-XXX (name)
- **Impact**: what an attacker can do
- **Fix**: specific code change
OWASP Top 10:2025 Quick Map
| # | Risk | Exploit | Defense |
|---|---|---|---|
| A01 | Broken Access Control | IDOR: /api/user/123 → /124 |
Auth check on EVERY endpoint, 404 not 403 |
| A02 | Security Misconfiguration | Default creds, debug, verbose errors, exposed files | Helmet, CSP, no defaults, generic errors, block dotfiles |
| A03 | Supply Chain | Compromised npm packages (Shai-Hulud: 500+) | Pin versions, npm ci --ignore-scripts, audit |
| A04 | Cryptographic Failures | Weak hashing, plaintext, broken TLS | Argon2id, AES-256-GCM, TLS 1.2+ only |
| A05 | Injection | SQLi, XSS, SSTI, prototype pollution, prompt injection | Parameterized queries, DOMPurify, no eval() |
| A06 | Insecure Design | No rate limit on login, no anti-automation | Rate limit, CAPTCHA, lockout |
| A07 | Auth Failures | JWT alg:none, weak secrets, no rotation |
jose + RS256, strong secrets, regenerate on login |
| A08 | Integrity Failures | Tampered CDN scripts, unsigned updates | SRI hashes, verify signatures |
| A09 | Logging Failures | No auth logging, secrets in logs | Log auth events, NEVER log tokens/passwords |
| A10 | Exception Mishandling | Stack traces + DB errors to client | Generic 500, detail to server logs only |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 106 lines · 61 tokens per session scan A 4d8d7a668f77
secure-coding is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,923 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fetch-url
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…