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 fix-pipeline-python-taskgit 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/fix-pipeline-python-task)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/fix-pipeline-python-task"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/fix-pipeline-python-task/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/fix-pipeline-python-task"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/fix-pipeline-python-task.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 | $0.00106 | $0.02320 |
| Opus 5.5 | $0.00042 | $0.00928 |
| Sonnet 5.5 | $0.00021 | $0.00464 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
fix-pipeline-python-task 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locate the script → check what it lands → fix → validate → confirm → merge/save. 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 — often already set). For git, $GITHUB_TOKEN is usually set. For schema checks you also need a warehouse credential (Snowflake/BigQuery) or S3/object-store credential — ask the user if not present.
If neither MCP nor an Orchestra 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.
Base: https://app.getorchestra.io/api/engine/public — header Authorization: Bearer $ORCHESTRA_API_KEY.
1. Inputs from identify-pipeline-error
identify-pipeline-error hands you: the pipeline run ID (RID), pipeline ID (PID), the failed Python task run ID (TRID), integration=PYTHON, the run branch/commit, the task's taskParameters, and the cause classification (a Python code / dependency / destination-schema issue). Use them directly — don't re-run the identification.
If invoked standalone (no handoff): run identify-pipeline-error first, or do its minimum yourself — GET /pipeline_runs?pipeline_run_ids=<RID> then GET /task_runs?pipeline_ids=<PID>&page_size=50 (filter to this RID client-side; pipeline_run_ids does not filter /task_runs, 7-day window) to find the FAILED Python task.
Capture taskParameters exactly — command/entrypoint, python_version, package_manager, requirements, branch, project_dir, and any env/run inputs. Preserve them on every retry. The pipeline run's branch is where the Orchestra YAML lives; the script's source branch (if git-backed) is a separate task param.
Pull the logs you'll fix against:
GET /pipeline_runs/<RID>/task_runs/<TRID>/logs # list filenames
GET /pipeline_runs/<RID>/task_runs/<TRID>/logs/download?filename=<file> # URL-encode spaces
Read the Python traceback bottom-up: the last exception line is the real error, not the first.
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 First seen · 116 lines · 106 tokens per session scan A 213f828b89d2
fix-pipeline-python-task is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 2,320 once invoked, about $0.0004 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.