observability-verification

observability-verification is a skill for Claude Code, Codex from telus-labs/stagecraft. It costs 65 tokens per session (2,549 once invoked), scanned A, original, MIT.

A check that compares the metrics, logs, and traces promised in a design with the signals actually produced by the released code. These signals help teams understand how software behaves in operation.

In plain words
What is it for?
Use it during the specified full or hotfix release checks to verify required monitoring signals and record the result.
Why use it?
It catches observability requirements that were documented but never implemented.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/telus-labs/stagecraft/observability-verification
Any agent
npx skills add telus-labs/stagecraft --skill observability-verification
Clone the repo
git clone --depth 1 https://github.com/telus-labs/stagecraft

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for observability-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/telus-labs/stagecraft/observability-verification.svg)](https://agentmods.dev/skills/telus-labs/stagecraft/observability-verification)
Your own site
<a href="https://agentmods.dev/skills/telus-labs/stagecraft/observability-verification"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/observability-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,549 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 5.1 $0.00065 $0.02549
Opus 5 $0.00032 $0.01274
Sonnet 5 $0.00013 $0.00510
Haiku 4.5 $0.00006 $0.00255

Measured 6d ago against content hash 4da50c3b48c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

observability-verification 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 6d 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.

skills/observability-verification/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observability verification

Use this skill at Stage 6c (observability gate) to verify that every metric, log, and trace the design-spec promised is actually emitted by the shipped code. The most common failure mode this catches: a design says "we'll emit a counter feature_x_changes_total" and the code never adds it.

When to use

  • Stage 6c runs on full and hotfix tracks. Those are the tracks where the brief's §9 "Observability requirements" is mandatory.
  • The platform role owns this stage; consult Backend/Frontend on what they actually added.

When to skip

This stage is not in nano, config-only, dep-update, quick tracks. If you're on one of those, this skill doesn't apply. If you're on full / hotfix and the brief genuinely has no observability requirements (rare), set every required array to [] and PASS the gate.

Procedure

1. Extract the required signals

Read pipeline/brief.md §9 "Observability requirements" and pipeline/design-spec.md for any expansion. Categorize each requirement:

  • Metrics: counters / gauges / histograms with specific names. Look for prose like "counter X with labels Y, Z" or explicit metric-name lists.
  • Logs: log statements with specific event types. Either named events (e.g. "log every opt-in change at INFO") or substring-matchable phrases.
  • Traces: span names. Many briefs don't require traces explicitly — check the design-spec for §Tracing or §Distributed-tracing sections.

Make three lists. Empty is fine for any category the brief doesn't require.

2. Verify each signal in the code

For each required signal, find concrete evidence in the shipped code:

Metrics — typical patterns to grep for:

  • Prometheus / OpenTelemetry: counter.add(...), Counter("name", ...), prometheus_client.Counter("name"), metrics.counter("name")
  • StatsD: statsd.increment("name.path"), dogstatsd.gauge
  • Build a regex: grep -rE "name|MetricName.replace(/_/g, '[._]')" — many libs normalize separators

Read the full file on GitHub · 223 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. 6d ago First seen · 223 lines · 65 tokens per session scan A 4da50c3b48c0

Subscribe to this mod's changes

observability-verification is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 2,549 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.

Related

Other skills, from other repositories

semantix

Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.

Gnosil/semantix · 47 tokens

semantix-guide

Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…

Gnosil/semantix · 115 tokens

intuitive-tests

Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…

MiaoDX/intuitive-flow · 154 tokens

intuitive-flow

Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…

MiaoDX/intuitive-flow · 98 tokens

intuitive-preflight

Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…

MiaoDX/intuitive-flow · 112 tokens

intuitive-squash

Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…

MiaoDX/intuitive-flow · 73 tokens