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 agentmods add rules/team-telnyx/ai/maingit clone --depth 1 https://github.com/team-telnyx/aiWhat 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 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
main 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
team-telnyx/ai — Cursor agent rules
The canonical source of truth is AGENTS.md at the repo root. This MDC
file holds the rules Cursor's agent must always have in context. Keep
in sync with AGENTS.md and .cursorrules when changing project-wide
guidance.
Hard rules (don't break these)
- Generated files: never hand-edit under
providers/claude/plugin/skills/orproviders/cursor/plugin/skills/. Edit the source underskills/and run./scripts/sync-skills.sh. - Per-package install/test:
npm ciand tests run from each package's directory, not the repo root. Don't introduce a root-level test runner. - Secrets: never commit credentials, API keys, or
.envfiles. - Conventional Commits: title prefix required (
feat:,fix:,chore:,docs:). Commits must be signed.
Where things live
skills/— canonical SKILL.md files (235+ skills).providers/{claude,cursor}/— synced fromskills/. Generated.plugins/opencode/— OpenCode plugin source.tools/{python,typescript,mcp,ffl-cli}/— agent toolkits.cli/— agent CLI source.inference/— Telnyx-hosted inference docs.guides/— operational guides.agent.json— top-level agent manifest (capabilities, auth, endpoints).
Per-package commands
| Package | Test/build |
|---|---|
cli/ |
cd cli && npm test |
tools/python/ |
cd tools/python && pytest |
tools/typescript/ |
cd tools/typescript && npm test |
tools/mcp/ |
cd tools/mcp && npm run build |
guides/ |
npm run test:guides (root) |
Editing skills
After touching anything under skills/, run:
./scripts/sync-skills.sh
Commit the sync output in the same PR as the skill source change.
Style
- TypeScript: ES2020+, strict mode, ESM where the package supports it.
- Python: 3.10+, PEP 8, type hints on public functions.
- Markdown: GitHub-flavored, ATX headings.
- One concern per PR.
For runtime-agent (consumer) guidance, see AGENTS.md §"Consuming this
repo as a runtime agent".
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.
- 2d ago First seen · 65 lines · 606 tokens per session scan A d55a7cde2ea5
main is a cursor rule published in the GitHub repository team-telnyx/ai (212 stars, last pushed 5d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 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 cursor rules, from other repositories
alive-agents
Sub-agent Dispatch System for alive-analysis. Auto-triggers specialist recommendations at each ALIVE stage. Use when advancing stages, asking for help on a specific analysis task, or when specialist expertise is needed (statistics, data quality, narrative, ethics).
alive-decisions
Analysis Decision Records (DR) for alive-analysis. Auto-checks methodology decisions before suggesting alternatives. Use when running /analysis-dr, during analysis stage transitions, or when methodology choices are being made.
alive-analysis
ALIVE analysis workflow for structured data analysis. Use when user discusses data analysis, metrics, A/B tests, experiments, monitoring, or asks analytical questions like 'why did X drop' or 'can we predict Y'.
cursor-rule-snippet
Cursor rule "cursor-rule-snippet" from wufunc/nova, covering memory management, session initialization, explicit remember, reflect and constitution protocol.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.