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/kid-sid/codex-spellbook/securitynpx skills add kid-sid/codex-spellbook --skill securitygit clone --depth 1 https://github.com/kid-sid/codex-spellbookWhat 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 | $0.00049 | $0.00806 |
| Opus 5 | $0.00024 | $0.00403 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
Secure the system at boundaries, minimize trust, and make risky behavior explicit in code, configuration, and review.
When to Activate
- Add a new auth or authorization flow
- Handle user input at an external boundary
- Write database queries or ORM filters
- Review secrets, tokens, or credential handling
- Audit dependencies for known vulnerabilities
- Threat-model a new feature or integration
- Review logging for security-critical events
OWASP Quick Reference
| Risk | Default Mitigation |
|---|---|
| Broken access control | Enforce authorization on every sensitive action |
| Cryptographic failures | Use standard libs and managed secrets |
| Injection | Parameterized queries, escaped templates |
| Insecure design | Threat-model before shipping privileged flows |
| Security misconfiguration | Harden defaults, disable debug in production |
| Vulnerable components | Scan dependencies continuously |
| Identification/auth failures | Strong session rotation and token expiry |
| Integrity failures | Verify signed artifacts and trusted inputs |
| Logging/monitoring failures | Emit actionable audit logs |
| SSRF | Restrict outbound targets and metadata access |
Secrets and Boundary Validation
| Preferred | Avoid |
|---|---|
| Runtime environment variables or secret managers | Hardcoded tokens in source |
.env.example placeholders |
Real secrets in sample files |
| Secret rotation playbooks | Long-lived shared credentials |
Rules:
- Validate at request, message, CLI, and job-input boundaries.
- Convert external data into typed internal models once.
- Do not scatter ad hoc validation deep inside core logic unless it enforces domain invariants.
SQL Injection and JWTs
BAD
query = f"SELECT * FROM users WHERE email = '{email}'"
cursor.execute(query)
GOOD
cursor.execute("SELECT * FROM users WHERE email = %s", (email,))
GOOD
await db.query("SELECT * FROM users WHERE email = $1", [email]);
| Rule | Why |
|---|---|
| Keep JWT lifetimes short | Limits replay window |
Validate iss, aud, exp, nbf |
Prevents token confusion |
| Prefer asymmetric signing for distributed verification | Better key separation |
| Store refresh tokens securely and revoke on reuse | Limits session theft |
| Never put secrets or mutable authorization state in JWT payloads | Tokens are bearer artifacts |
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.
- 2d ago First seen · 116 lines · 49 tokens per session scan A 5bdd9fef262a
security is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 806 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.