dev-session

A command that starts a local Logfire development session and connects a running application to trace viewing. Traces are records of what an application does while handling requests or jobs.

In plain words
What is it for?
It is for starting a temporary tracing session, injecting the returned settings into an app, and viewing its local traces in Logfire.
Why use it?
It makes local debugging easier by supplying temporary connection details and a session-specific place to inspect application behavior.

Command

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 commands/pydantic/skills/dev-session
Clone the repo
git clone --depth 1 https://github.com/pydantic/skills
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,515 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 $0.00019 $0.01515
Opus 5 $0.00010 $0.00758
Sonnet 5 $0.00004 $0.00303
Haiku 4.5 $0.00002 $0.00152

Measured 2d ago against content hash 09399b7e82f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-session 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.

plugins/logfire/commands/dev-session.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-session

Start a local Logfire dev session that creates temporary credentials and injects them into your app so you can view traces in the Logfire UI.

Prerequisites

The Logfire MCP server must be connected (this plugin configures it automatically).

Workflow

Step 1: Create the dev session

Call the mcp__logfire__local_dev_session MCP tool to provision a temporary dev project and get credentials. This returns:

  • Logfire SDK env vars (LOGFIRE_TOKEN, LOGFIRE_BASE_URL)
  • Plain OTEL env vars (OTEL_EXPORTER_OTLP_ENDPOINT, OTEL_EXPORTER_OTLP_HEADERS, etc.)
  • OTEL_RESOURCE_ATTRIBUTES with a session tag for filtering traces
  • A Logfire UI link to view traces

Save all returned values — you will need them in the injection step.

Step 2: Analyze the codebase

Determine how the app is run and configured by scanning for:

  • Env files: .env, .env.local, .env.development
  • Container orchestration: docker-compose.yml / docker-compose.yaml, Kubernetes manifests (k8s/, deploy/, *.yaml with kind: Deployment)
  • Dev tools: Tiltfile (Tilt), skaffold.yaml (Skaffold), devcontainer.json / .devcontainer/
  • Process managers: Procfile (foreman/honcho)
  • Build/run targets: Makefile, justfile with dev/run targets
  • Deployment config: fly.toml, helmfile.yaml, Helm values.yaml
  • Framework conventions: Next.js uses .env.local, Python apps typically use .env

Also check whether Logfire or OpenTelemetry is already instrumented:

  • Look for logfire in Python dependencies, @pydantic/logfire-node or logfire in package.json, logfire in Cargo.toml
  • Look for OpenTelemetry SDK imports without Logfire
  • If the app is not instrumented at all, tell the user and suggest running /instrument first. The dev session credentials will still work once instrumentation is added, so continue with injection.

Step 3: Inject credentials

Choose the best injection method based on what you found. Prefer methods that support hot reload so the user doesn't have to restart manually.

Read the full file on GitHub · 117 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 · 117 lines · 19 tokens per session scan A 09399b7e82f2

Subscribe to this mod's changes

dev-session is a command published in the GitHub repository pydantic/skills (127 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,515 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.