What is triage-orchestra-pipeline?

A guided investigation for a failed Orchestra pipeline that opens a fix pull request and tests the proposed change on a branch. A pull request is a reviewable proposal to merge code into the main project.

Use it to investigate a failed or misbehaving pipeline, create and validate a fix pull request, summarise the findings, and wait for approval before merging.

It gives developers a human-readable diagnosis and a tested proposal without merging anything automatically. This preserves a review step before a fix reaches the main branch.

triage-orchestra-pipeline — Skill for Claude Code by orchestra-hq

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.

Any agent

npx skills add orchestra-hq/orchestra-skills --skill triage-orchestra-pipeline

Clone the repo

git clone --depth 1 https://github.com/orchestra-hq/orchestra-skills

Made for: Claude Code.

Or install orchestra, the plugin that ships this one along with the rest of its 19 skills, 1 hook.

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/orchestra-hq/orchestra-skills/triage-orchestra-pipeline/github.svg)](https://agentmods.dev/skills/orchestra-hq/orchestra-skills/triage-orchestra-pipeline)

Your own site

<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/triage-orchestra-pipeline"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/triage-orchestra-pipeline/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/orchestra-hq/orchestra-skills/triage-orchestra-pipeline"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/triage-orchestra-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,116 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.

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	$0.00153	$0.03116
Opus 5.5	$0.00061	$0.01246
Sonnet 5.5	$0.00031	$0.00623
Haiku 4.5	$0.00015	$0.00312

Measured 1mo ago against content hash a9519ea698fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage-orchestra-pipeline 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 1mo 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/orchestra/skills/triage-orchestra-pipeline/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Orchestra Pipeline

Diagnose a failed (or symptom-reported) pipeline, open a fix PR, validate it on the branch, then present a compact triage report and stop for human approval. Nothing merges to main until the user says so.

Shared references

Orchestra docs live under references/orchestra/. Index and layout: ../../references/orchestra/README.md. Paths below are relative to this skill folder.

Pipeline

../../references/orchestra/pipeline/diagnosis-patterns.md — error classification
../../references/orchestra/pipeline/remediation-playbooks.md — fix strategies
../../references/orchestra/pipeline/knowledge-store.md — (optional) local fix history; prefer your client's persistent memory

MCP

../../references/orchestra/mcp/tools-quick-ref.md — tool arguments and behaviour (use get_pipeline to read a pipeline's full definition)

Workflow

Step 0 — Parse the prompt: error-first or symptom-first?

Before doing anything, classify the input:

Error-first — the pipeline has a red status, or the user gives a run ID/URL/UUID, or says "my pipeline failed". Skip to Step 1.

Symptom-first — the user describes something wrong in a downstream system without mentioning a pipeline error: "Lightdash dashboard looks wrong", "numbers are off", "chart is stale", "dbt model returning bad values". Go to Step 0b.

Step 0b — Symptom-first: start at the named layer, traverse upstream

Goal: Find the root cause by starting at the system the user named and walking backwards through the pipeline until something is wrong.

0b-1. Map the symptom to a pipeline task

Extract the system keyword from the prompt (e.g. "Lightdash", "dbt", "Fivetran"). Call list_pipeline_runs for the relevant pipeline to get the most recent run. Call list_task_runs for that run to get all tasks and their execution order.

Match the keyword to a task via the integration field (e.g. LIGHTDASH, DBT_CORE, FIVETRAN). This is the entry task. If no pipeline is named, ask the user which pipeline to check before proceeding.

Read the full file on GitHub · 321 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.

1mo ago Changed · +3 lines a9519ea698fa
1mo ago First seen · 318 lines · 153 tokens per session scan A 4af805a30542

Subscribe to this mod's changes

triage-orchestra-pipeline is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 3,116 once invoked, about $0.0006 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 2026-09-09.

Debugging Git and workflow

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

enable-check-includes-strict

Enable and migrate Chromium targets and directories to checkincludesstrict = true, diagnosing and resolving header include violations as part of the checkincludesstrict LSC. Use when adding directories to the allowlist, enabling strict header checks on targets, or resolving CHECKINCLUDESSTRICTUNTRIAGED targets.

chromium/chromium · 70 tokens

triage-orchestra-pipeline