Dograh is an open-source, self-hostable platform for building voice AI agents that combine speech recognition, language models, and speech synthesis. Teams use its visual workflow builder and telephony integrations to create and operate voice agents while choosing their own providers and infrastructure.
Borrowing it
Nothing to install: this file belongs to dograh-hq/dograh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dograh-hq/dograh/main/.agents/skills/merge-pipecat-upstream/SKILL.mdgit clone --depth 1 https://github.com/dograh-hq/dograhWrote 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/dograh-hq/dograh/merge-pipecat-upstream)<a href="https://agentmods.dev/skills/dograh-hq/dograh/merge-pipecat-upstream"><img src="https://agentmods.dev/badge/skills/dograh-hq/dograh/merge-pipecat-upstream/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/dograh-hq/dograh/merge-pipecat-upstream"><img src="https://agentmods.dev/badge/skills/dograh-hq/dograh/merge-pipecat-upstream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.01934 |
| Opus 5 | $0.00051 | $0.00967 |
| Sonnet 5 | $0.00020 | $0.00387 |
| Haiku 4.5 | $0.00010 | $0.00193 |
Grade A, and why
merge-pipecat-upstream 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 3d 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.
Merging upstream pipecat
pipecat/ is a git submodule of the fork dograh-hq/pipecat (origin), installed editable by scripts/setup_requirements.sh. Upstream is https://github.com/pipecat-ai/pipecat and is usually not configured as a remote. Fork main is the integration branch; the dograh repo pins a commit of it via the submodule pointer.
Dograh customization lives in two layers, and both must be audited on every merge:
- In-fork changes — dograh-owned modules that don't exist upstream (
src/pipecat/services/dograh/, serializers likevobiz.py/cloudonix.py/asterisk.py,call_strategies.py,tests/test_dograh_services.py) plus patches to upstream files (aggregators, transports, turn tracking, serializers). - api/-side wrappers — subclasses in the dograh repo (
api/services/pipecat/,api/services/telephony/providers/*/,api/services/workflow/pipecat_engine*.py) that override upstream hooks and reach into private state (self._session,self._bot_is_responding, …). These break silently on upstream refactors — no merge conflict, no import error.
Freshness rule: trust the current repos over any inventory in this file. Discover state with the commands below; don't assume file lists here are complete.
1. Baseline and setup
cd pipecat
git log --first-parent --oneline --merges | grep -m1 "Merge tag" # OLD_TAG = last merged upstream tag
git remote add upstream https://github.com/pipecat-ai/pipecat.git 2>/dev/null
git fetch upstream --tags
git tag --sort=-v:refname | head -5 # pick NEW_TAG (latest stable)
git checkout -b merge-vNEW origin/main
In the dograh repo, work on a bump-pipecat-X.Y branch.
2. Recon before merging
Do this before git merge — conflict resolution decisions must be made from evidence, not on the fly.
git diff NEW_TAG...origin/main --stat -- src tests # full surviving dograh delta (three-dot = from merge-base)
git log --first-parent --oneline OLD_MERGE_COMMIT..origin/main # dograh commits since last merge
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.
- 3d ago Changed · +19 lines 455b9b8c22eb
- 11d ago First seen · 97 lines · 102 tokens per session scan A bad8f9eb2636
merge-pipecat-upstream is a skill published in the GitHub repository dograh-hq/dograh (5,621 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 102 tokens to every session and 1,934 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
perseus
Use when you need a bounded, local Perseus context render before an assistant reads project state. Perseus resolves selected workspace inputs such as git, services, sessions, and task notes into markdown. Use for deterministic session starts, workspace audits, and explicit context handoffs.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
qai-marketing
Acts as the QAI Consultant marketing/PR specialist. Use whenever Gabi asks to write, draft, or plan a social media post (LinkedIn, Facebook, Instagram) promoting the QAI Consultant app or MCP server - release announcements, educational QA tips, milestones, case studies, or behind-the-scenes. Covers Romanian and…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.