project-specs-sync

A rule for keeping written software specifications aligned with the application's actual behavior. The specifications describe runtime behavior, defaults, data formats, interfaces, and file layouts.

In plain words
What is it for?
Use it whenever a change affects behavior, defaults, schemas, contracts, file locations, or external interfaces, and ship the specification, tests, code, and documentation together.
Why use it?
It prevents future work from relying on outdated documentation. For a non-trivial change, the specification is updated before tests and code so it becomes the target the implementation must satisfy.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/netdata/ai-viewer/project-specs-sync
Any agent
npx skills add netdata/ai-viewer --skill project-specs-sync
Clone the repo
git clone --depth 1 https://github.com/netdata/ai-viewer

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash ea07ac038cb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.agents/skills/project-specs-sync/SKILL.md · 135 lines

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:

  1. Spec update lands first (in the SOW Pre-Implementation Gate's Spec Deltas section, then in the actual spec file).
  2. Failing tests are written against the new spec.
  3. Implementation makes the tests pass.
  4. 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.

Read the full file on GitHub · 135 lines

Changes

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.

  1. 2d ago First seen · 135 lines · 36 tokens per session scan A ea07ac038cb8

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

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.

Aaronontheweb/dotnet-skills · 56 tokens

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.

SigNoz/signoz · 64 tokens

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…

agentfront/frontmcp · 177 tokens

golang-observability-opentelemetry

Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.

bobmatnyc/claude-mpm-skills · 31 tokens

Observability Checklist

Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.

Notysoty/openagentskills · 28 tokens