pixir-diagnostics

An evidence-based diagnostic workflow for Pixir and T3 Code Pixir sessions. Pixir is a runtime for agent sessions and subagents; T3 Code is a coding environment that can use it.

In plain words
What is it for?
Use it when a Pixir run, subagent, workflow, provider replay, or dogfooding session is stuck, inconsistent, missing tool output, or difficult to classify.
Why use it?
It helps distinguish facts in session logs from symptoms caused by the user interface, adapters, service providers, or summaries.

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/ranvier-technologies/pixir/pixir-diagnostics
Any agent
npx skills add Ranvier-Technologies/pixir --skill pixir-diagnostics
Clone the repo
git clone --depth 1 https://github.com/Ranvier-Technologies/pixir

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,176 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 $0.00061 $0.01176
Opus 5 $0.00030 $0.00588
Sonnet 5 $0.00012 $0.00235
Haiku 4.5 $0.00006 $0.00118

Measured 2d ago against content hash d7457db89444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pixir-diagnostics 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/pixir-diagnostics/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixir Diagnostics

Use this Skill when Pixir, a Pixir-backed T3 Code thread, or a Pixir Session needs an evidence-backed diagnosis. The goal is to separate canonical Pixir facts from UI, adapter, provider, or assistant-summary symptoms.

This Skill is procedural. Prefer existing Pixir commands first; do not build a new script unless the same manual bundle is repeated enough to justify automation.

Evidence Model

Rank evidence in this order:

  1. Pixir canonical NDJSON Logs under .pixir/sessions/ and child .pixir/subagents/.
  2. Pixir diagnostic commands: doctor, diagnose session, inspect-replay, tree.
  3. T3 Code durable storage or logs.
  4. Screenshots or visible UI state.
  5. Assistant summaries inside the conversation.

Assistant summaries are never proof when they contradict Logs.

Default Workflow

  1. Identify the workspace that owns the Session Log.
  2. Identify the Pixir binary actually used:
    • source checkout: ./pixir
    • Hex install: pixir on PATH
    • T3 provider config: binaryPath
  3. Run local readiness:
pixir doctor --json
  1. If a Pixir Session id is known, run:
pixir diagnose session <session-id> --json
pixir inspect-replay <session-id> --json
pixir tree <session-id> --json
  1. If a T3 thread id is known, locate T3 durable state before guessing:
find "$HOME/Library/Application Support" -maxdepth 3 -iname '*t3*' -print

Then search bounded patterns such as the thread id, Pixir session id, or exact UI error text. Avoid dumping whole LevelDB records into chat.

  1. Produce a short verdict with:
    • classification,
    • evidence paths,
    • pass/fail/warning checks,
    • next action,
    • what not to infer.

Command Surface

Use the repo binary when testing source changes:

mix escript.build
./pixir --version
./pixir doctor --json
./pixir diagnose session <session-id> --json
./pixir inspect-replay <session-id> --after-seq <n> --json
./pixir tree <session-id> --json

Use the Hex binary when diagnosing the installed daily-driver path:

Read the full file on GitHub · 141 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 · 141 lines · 61 tokens per session scan A d7457db89444

Subscribe to this mod's changes

pixir-diagnostics is a skill published in the GitHub repository Ranvier-Technologies/pixir (23 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 1,176 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 2026-08-30.

Related

Other skills, from other repositories

cross-linker

Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the…

saski/arnesto · 137 tokens

free-agent-execution

Run an explicitly requested, bounded, non-sensitive coding task through the local free-worker adapter using a verified free OpenCode model. Use only when the user asks to execute a free worker or free agent and accepts the external-model safety boundary.

saski/arnesto · 52 tokens

google-adk-agent-patterns

Define, compose, and wire Google ADK agents with function tools and multi-agent orchestration. Use when writing agent definitions, adding Python function tools, building pipelines with SequentialAgent/LoopAgent/ParallelAgent, or designing router/delegation patterns. Trigger on: adk agent, LlmAgent, SequentialAgent…

saski/arnesto · 92 tokens

corporate-aws-cli

Use when using the AWS CLI against a corporate AWS account after SAML/OIDC federation (e.g. saml2aws, aws sso login), when STS fails with invalid XML or empty responses, when selecting profiles or regions for Terraform or CI/CD stacks, or when validating RDS engine versions with describe-orderable-db-instance-options…

saski/arnesto · 81 tokens

google-adk-setup

Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk…

saski/arnesto · 83 tokens

align

Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives. Use when aligning on a design, plan, or technical approach before implementation.

saski/arnesto · 33 tokens