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-specs-syncnpx skills add netdata/ai-viewer --skill project-specs-syncgit clone --depth 1 https://github.com/netdata/ai-viewerWhat 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 | $0.00036 | $0.01695 |
| Opus 5 | $0.00018 | $0.00847 |
| Sonnet 5 | $0.00007 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
project-specs-sync 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specs Sync
Why
Specs under .agents/sow/specs/ are the assistant's durable memory of what ai-viewer does. The operator does not read specs. The assistant writes specs for itself — for the next session, the next compaction, the next reviewer. When code drifts from specs, the assistant is silently betraying future-self: future SOWs base plans on a spec that no longer matches reality.
Core Rule: Specs Lead
Specs change first, before tests, before code. This is the inverse of the common "document at the end" pattern. The reasoning: a spec that describes the target behavior turns into the executable contract — tests are written against the spec, code makes the tests pass against the spec. If the spec lags, the implementation has nothing to be judged against.
The order on any non-trivial change:
- Spec update lands first (in the SOW Pre-Implementation Gate's
Spec Deltassection, then in the actual spec file). - Failing tests are written against the new spec.
- Implementation makes the tests pass.
- All four (spec + tests + code + docs) ship in a single commit.
Drift between spec and code is a regression by definition.
When Specs Must Update
| Code change | Spec(s) to update |
|---|---|
| Adapter parsing change | adapter-<name>.md |
| Canonical event type change | canonical-events.md |
| SQLite schema change | data-model.md |
| REST endpoint change | rest-api.md |
| SSE event type change | sse-protocol.md |
| New UI route or page | ui-pages.md |
| Frontend state pattern change | frontend-architecture.md |
| Ingester behavior change | ingester.md |
| Server behavior change | presenter.md |
| New default value | wherever it's documented |
| Bind/port/path default change | deployment.md |
| Security-relevant change | security.md |
| New external dependency | the package's spec + AGENTS.md tech-stack table |
| Test strategy change | testing-strategy.md |
| Health/logging change | observability.md |
If the relevant spec doesn't exist: create it in the same commit. If multiple specs are affected: update all.
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 · 135 lines · 36 tokens per session scan A ea07ac038cb8
project-specs-sync is a skill published in the GitHub repository netdata/ai-viewer (2 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,695 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 2026-08-31.
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.
Observability Checklist
Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.