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 merge-duplicate-pipelinesgit 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/merge-duplicate-pipelines)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/merge-duplicate-pipelines"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/merge-duplicate-pipelines/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/merge-duplicate-pipelines"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/merge-duplicate-pipelines.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 | $0.00223 | $0.02434 |
| Opus 5.5 | $0.00089 | $0.00974 |
| Sonnet 5.5 | $0.00045 | $0.00487 |
| Haiku 4.5 | $0.00022 | $0.00243 |
Grade A, and why
merge-duplicate-pipelines scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Duplicate Pipelines
Find pipelines in an Orchestra workspace that are the same process duplicated — across environments or conceptually — and consolidate each duplicate set into one pipeline with the right parameterisation in place of the copy-paste. Detection is read-only; anything that changes a pipeline requires an explicit choice from the user for that specific set.
References
../../references/orchestra/mcp/tools-quick-ref.md— MCP tool names and arguments.../../references/orchestra/pipeline/yaml-authoring.md— schema and variable syntax (${{ ENV.* }},${{ inputs.* }},${{ MATRIX.* }}, conditions).references/detection-and-patterns.md— read this before drafting anything. The similarity heuristic in full, the ENV-LABELED vs CONCEPTUAL classification, and before/after YAML for each consolidation pattern.../account-health-check/references/best-practices-checklist.mdchecks 1.1 (one pipeline per process, not per environment), 1.3 (MetaEngine instead of duplicated tasks/pipelines), 1.9 (inputs/env vars/conditionals over duplication), and 2.1 (don't run one pipeline per environment) — this skill is the fix for those findings.
Workflow
Step 0 — Fresh detection, or acting on an existing report?
If the user hands you an existing account-review report, or pastes findings that name checks 1.1/1.3/1.9/2.1, read it for the pipelines it already flagged and skip straight to Step 3 with those as your starting candidate set — no need to re-scan the account. Otherwise start at Step 1.
Step 1 — Access and scope
Same access pattern as account-health-check: use the Orchestra MCP if connected
(list_pipelines, get_pipeline); otherwise fall back to the REST API with
$ORCHESTRA_API_KEY (https://app.getorchestra.io/api/engine/public). If neither is
available, point the user at the MCP setup docs and stop.
Tell the user which workspace you're scanning and confirm scope: full account, or a named
subset. For large workspaces, default to the live + Git-backed set (every unpaused,
recently-run pipeline plus every Git-backed one) for the same reason account-health-check
does — reading every definition has a real cost — and say what you skipped.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed 7bbe0a53c049
- 1mo ago First seen · 177 lines · 223 tokens per session scan A 6416f1719081
merge-duplicate-pipelines is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 223 tokens to every session and 2,434 once invoked, about $0.0009 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…