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.
git clone --depth 1 https://github.com/ahkedia/lyra-aiWrote 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/rules/ahkedia/lyra-ai/lyra-git-workflow)<a href="https://agentmods.dev/rules/ahkedia/lyra-ai/lyra-git-workflow"><img src="https://agentmods.dev/badge/rules/ahkedia/lyra-ai/lyra-git-workflow/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/rules/ahkedia/lyra-ai/lyra-git-workflow"><img src="https://agentmods.dev/badge/rules/ahkedia/lyra-ai/lyra-git-workflow.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 | $0.00382 | $0.00382 |
| Opus 5.5 | $0.00153 | $0.00153 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
lyra-git-workflow 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.
What it actually says
Lyra — Git & deploy (mandatory)
Read docs/GIT-WORKFLOW.md for the full contract. On every task that changes tracked files:
Two repos — route changes to the RIGHT one (mandatory)
| Change | Repo |
|---|---|
| Code, scripts, plugins, skills, evals, docs, templates | lyra-ai (public, this repo) |
Live SOUL.md / MEMORY.md / HEARTBEAT.md, cron-jobs.json, notion/notion.md, phone numbers, personal facts |
lyra-private (PRIVATE, /root/lyra-private on Hetzner) |
Never commit personal data here — a pre-push PII hook (scripts/pii-scan.sh) and CI will reject it; do NOT bypass with --no-verify. Cron changes go to lyra-private/config/cron-jobs.json (mirror of /root/.openclaw/cron/jobs.json), not this repo. Full design: docs/12-public-private-split.md.
- Start:
git fetch origin && git pull --ff-only origin main(from the project root). If--ff-onlyfails, stop and fix divergence before editing. - End:
git add→git commitwith a clear message →git push origin main. - VPS: Do not commit only on the server. Deploy with pull from
main+ service restart when needed; seedocs/GIT-WORKFLOW.md.
The human may not use the terminal; you run these commands when implementing work. No silent local-only state.
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 · 24 lines · 382 tokens per session scan A 062bb6b11e94
lyra-git-workflow is a cursor rule published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 1mo ago), licensed MIT. It adds 382 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
desktop-release-gate
Desktop app fixes must pass a local packaged build smoke test before pushing release tags or CI desktop builds.
nauro-ship-task
Run the full planner -> executor -> reviewer -> tech-lead -> direct-user-confirm -> push chain through Cursor's native project workflow agents. Requires the four bundled .cursor/agents/nauro-.md definitions and fails closed without native dispatch.
roslyn-mcp-version-bump
Auto-bump Version after successful MCP self-build and reload.
backend-python
Cursor rule "backend-python" from coeusyk/inference-x, covering backend python rules, stack assumptions, code style, fastapi conventions and schema conventions.
git_workflow
Git Workflow and Configuration for AGB SDK.
sciclaw-papercuts
Papercuts from Sol/ImageMagick/release cycles — release, brew, CI, and workspace hygiene for sciClaw agents.