What is 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.

Use it when a Pixir run, subagent, workflow, provider replay, or dogfooding session is stuck, inconsistent, missing tool output, or difficult to classify.

It helps distinguish facts in session logs from symptoms caused by the user interface, adapters, service providers, or summaries.

How Ranvier-Technologies/pixir configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Ranvier-Technologies/pixir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Ranvier-Technologies/pixir/main/.agents/skills/pixir-diagnostics/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Ranvier-Technologies/pixir

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ranvier-technologies/pixir/pixir-diagnostics/github.svg)](https://agentmods.dev/skills/ranvier-technologies/pixir/pixir-diagnostics)

Your own site

<a href="https://agentmods.dev/skills/ranvier-technologies/pixir/pixir-diagnostics"><img src="https://agentmods.dev/badge/skills/ranvier-technologies/pixir/pixir-diagnostics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ranvier-technologies/pixir/pixir-diagnostics"><img src="https://agentmods.dev/badge/skills/ranvier-technologies/pixir/pixir-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.01176
Opus 5.5	$0.00024	$0.00470
Sonnet 5.5	$0.00012	$0.00235
Haiku 4.5	$0.00006	$0.00118

Measured 2mo ago against content hash d7457db89444, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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:

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

Assistant summaries are never proof when they contradict Logs.

Default Workflow

Identify the workspace that owns the Session Log.
Identify the Pixir binary actually used:
- source checkout: ./pixir
- Hex install: pixir on PATH
- T3 provider config: binaryPath
Run local readiness:

pixir doctor --json

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

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.

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.

2mo 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 (24 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,176 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents Debugging acp agent-harness coding-agents developer-tools elixir otp

pixir-diagnostics next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pixir-diagnosticsRanvier-Technologies/pixir	Skill	24	1mo ago	MIT	A	61	Claude Code
runtime-evidence-and-tracingyfge/agent-harness-skills	Skill	12	2d ago	MIT	A	39	Claude Code
lustrasaski/arnesto	Skill	6	4d ago	Unlicense	A	258	Claude Code
source-command-bug-fixing-agentsaski/arnesto	Skill	6	4d ago	Unlicense	A	72	Claude Code, Codex
xp-mikado-methodsaski/arnesto	Skill	6	4d ago	Unlicense	A	45	Claude Code, Codex
xp-simple-design-refactorsaski/arnesto	Skill	6	4d ago	Unlicense	A	41	Claude Code, Codex
xp-predict-problemssaski/arnesto	Skill	6	4d ago	Unlicense	A	36	Claude Code, Codex

pixir: Skill for Claude Code