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/hoavdc/codexkit/codexkit-cloud-delegationnpx skills add hoavdc/CodexKit --skill codexkit-cloud-delegationgit clone --depth 1 https://github.com/hoavdc/CodexKitWhat 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 | $0.00028 | $0.00430 |
| Opus 5 | $0.00014 | $0.00215 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
codexkit-cloud-delegation 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 yesterday.
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.
What it actually says
Cloud Delegation
Use this skill when the task is large enough to benefit from multiple Codex runs, worktrees, or specialized passes.
Workflow
- Separate blocking work from parallel sidecar work.
- Assign each delegated task a narrow objective and write scope.
- Require the delegated worker to report changed files and validation run.
- Integrate results quickly instead of waiting on every branch.
- Keep final synthesis centralized.
Good delegated tasks
- isolated test authoring
- docs updates after implementation
- codebase reconnaissance on a bounded topic
- verification passes that can run while implementation continues
Avoid
- delegating the immediate critical path
- overlapping write scopes
- vague asks like "analyze everything"
Quality Criteria
- All dependencies and prerequisites are documented
- Changes are reversible or include a rollback plan
- Security implications are assessed for each configuration change
- Monitoring and alerting are defined for post-deployment validation
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Are all configurations, permissions, and dependencies accurate? |
| Completeness | Does the setup cover dev, staging, and prod environments as needed? |
| Context-fit | Is the solution proportional to the problem (not over/under-engineered)? |
| Consequence | If deployed as-is to production, what is the highest-risk failure mode? |
Edge Cases
- Target environment has pre-existing configuration — Scan for conflicts before applying changes. Document what to preserve.
- Permissions differ between environments — Test in staging first. Document the minimum permissions required.
- Third-party service is unavailable or deprecated — Document fallback or alternative. Include health-check endpoints.
Changelog
- v1.0.0 — Initial release
What ships with it
1 file 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.
- yesterday First seen · 58 lines · 28 tokens per session scan A 9aedf4a99d46
codexkit-cloud-delegation is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 430 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 2026-08-30.
Other skills, from other repositories
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
analyzing-security
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
checking-code-quality
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.