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.
npx skills add orchestra-hq/orchestra-skills --skill identify-pipeline-errorgit clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote 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.
[](https://agentmods.dev/skills/orchestra-hq/orchestra-skills/identify-pipeline-error)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/identify-pipeline-error"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/identify-pipeline-error/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.
<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/identify-pipeline-error"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/identify-pipeline-error.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00210 | $0.03017 |
| Opus 5.5 | $0.00084 | $0.01207 |
| Sonnet 5.5 | $0.00042 | $0.00603 |
| Haiku 4.5 | $0.00021 | $0.00302 |
Grade A, and why
identify-pipeline-error 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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identify Pipeline Error
The router. Identify which task broke and why, then route to the skill that fixes it.
This skill draws a clean line: it identifies and classifies; the fix-* skills fix. Do not
attempt code repairs, schema changes, or branch validation here — that is the fixer's job.
Narrate each step briefly, like a data engineer. Never print secrets/tokens.
0. Access
MCP is preferred but optional. If the Orchestra MCP tools aren't present, use the public REST API
with $ORCHESTRA_API_KEY (check the env — it's often already set). If neither MCP nor a key is
available, point the user at the Orchestra MCP setup docs (https://docs.getorchestra.io/docs/mcp)
or ask for an API key, then stop.
- MCP, composite:
whats_broken,diagnose,pipeline_context— each answers a whole step below in one call. Prefer them (see §1a). - MCP, granular:
list_pipeline_runs,list_task_runs,list_operations,list_task_run_logs,download_task_run_log,list_task_run_artifacts,list_pipelines— see../../references/orchestra/mcp/tools-quick-ref.md. - REST base:
https://app.getorchestra.io/api/engine/public— headerAuthorization: Bearer $ORCHESTRA_API_KEY.
If a call comes back 403, the workspace does not have the Metadata API enabled. Say so and ask the user to have a workspace admin enable it — do not retry or fall back to guessing.
1a. The fast path — two calls, when the composite tools are present
If whats_broken and diagnose are available, they collapse Steps 1-3 and you should
reach for them first. Steps 1-3 remain the fallback for a client without them, or for
anything they do not cover.
| You have | Call | You get |
|---|---|---|
| Nothing — "what's broken?" | whats_broken() |
Every failing run in the last 24h, each with its failed tasks, messages and anomalies. Widen with window_hours, narrow with environment. |
| A pipeline run ID or URL | whats_broken(), then pick the run by ID |
The same digest; the run you want is in it if it failed inside the window |
| A task run ID | diagnose(task_run_id) |
Parameters, upstream statuses, log tail, artifact names |
| A pipeline name, alias or ID | pipeline_context(alias) |
Definition, integrations, recent outcomes, duration baseline |
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 · +28 lines c4e3b28311be
- 1mo ago First seen · 173 lines · 210 tokens per session scan A da71f9498d60
identify-pipeline-error is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 210 tokens to every session and 3,017 once invoked, about $0.0008 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.