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/netdata/ai-viewer/project-delegationnpx skills add netdata/ai-viewer --skill project-delegationgit clone --depth 1 https://github.com/netdata/ai-viewerWrote 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/netdata/ai-viewer/project-delegation)<a href="https://agentmods.dev/skills/netdata/ai-viewer/project-delegation"><img src="https://agentmods.dev/badge/skills/netdata/ai-viewer/project-delegation.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 | $0.00054 | $0.01307 |
| Opus 5 | $0.00027 | $0.00654 |
| Sonnet 5 | $0.00011 | $0.00261 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
project-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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation
The Rule
The CTO owns implementation. Helper subagents are optional tools for bounded investigation or summarization. They do not own code, tests, plans, commits, or reviews.
Use helpers when:
- many files need read-only inspection;
- independent investigations can run in parallel;
- a concise evidence summary would preserve master context;
- the task is exploratory and has a clear, bounded question.
Do not use helpers when:
- the CTO has not yet done the core thinking;
- the task is normal implementation work;
- the output would be accepted without local verification;
- the job is an external reviewer gate. Use
project-second-opinionsfor that.
What "Production Code" Means Here
Files that go into a release artifact or affect runtime behavior:
cmd/**/*.gointernal/**/*.gofrontend/src/**frontend/tests/**scripts/*.shonce they are used in CI.github/workflows/**- Any SQL migration
The CTO may edit production code directly after the spec/test/code workflow allows it. This skill is not a restriction on direct implementation.
Available Subagent Types
The Agent tool exposes specialized subagent types. For ai-viewer work:
| Subagent type | When to use |
|---|---|
general-purpose |
Broad read-only investigation or summarization when specialized helpers are not needed. Not the default code producer. |
Explore |
read-only search; "where is X defined", "which files reference Y", quick file-by-pattern lookups. Bounded; doesn't read whole files. |
Plan |
Optional plan critique or decomposition input. CTO owns the plan. |
code-reviewer |
Local helper review for quick feedback. This does not replace external reviewer gates. |
code-simplifier |
Optional readability suggestions. CTO verifies before editing. |
typescript-pro |
Optional TypeScript/type-system advice for frontend/. CTO owns any edits. |
deep-research |
multi-source research (online docs, mirrored repos, RFCs) when planning a new feature or adapter. |
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.
- 4d ago First seen · 148 lines · 54 tokens per session scan A f5ec43706480
project-delegation is a skill published in the GitHub repository netdata/ai-viewer (2 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,307 once invoked, about $0.0003 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 skills, from other repositories
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
openui-forge-zh
使用 OpenUI 构建生成式 UI 应用 — 支持任意 LLM 提供商、任意后端语言。脚手架、集成、验证。.