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 agents/praveenjuge/teak/headless-developmentgit clone --depth 1 https://github.com/praveenjuge/teakWrote 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/agents/praveenjuge/teak/headless-development)<a href="https://agentmods.dev/agents/praveenjuge/teak/headless-development"><img src="https://agentmods.dev/badge/agents/praveenjuge/teak/headless-development.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00429 |
| Opus 5 | $0.00000 | $0.00215 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
headless-development 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 5d 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
Headless development
Use this guide only in Cursor Cloud or another headless VM. For local development, use the normal root scripts.
Runtime
Read the required Bun version from the root packageManager field. Install that exact version if Bun is unavailable, then run bun install --frozen-lockfile from the repository root.
turbo watch defaults to an interactive UI. In a headless session, set TURBO_UI=false for streaming output or run the required services separately.
Minimal web stack
Start Convex from packages/convex in a persistent session:
export CONVEX_AGENT_MODE=anonymous
bun run dev
Start the web app from apps/web in another persistent session:
bunx portless app.teak next dev
Use the localhost URL printed by Portless. Do not assume a fixed port.
Create apps/web/.env.local from the active Convex deployment values. A local anonymous deployment normally uses:
NEXT_PUBLIC_CONVEX_URL=http://127.0.0.1:3210
NEXT_PUBLIC_CONVEX_SITE_URL=http://127.0.0.1:3211
First-run authentication
Set the anonymous Convex deployment's Google client values, SITE_URL, and JWKS. Test values are acceptable for OAuth credentials in local development. Generate JWKS as the array expected by the installed @convex-dev/better-auth version; consult its current documentation instead of copying a stale shape.
Better Auth validates the browser origin. If authentication reports Invalid origin, set SITE_URL to the exact browser origin, wait for Convex to redeploy, and retry.
Test users can be marked verified through the existing internal test-setup endpoint. Inspect its current validator and route before calling it; do not cache a request contract here.
The environment is ready when Convex and the web app remain running, the login page loads at the printed localhost URL, and a test session can authenticate without an origin error.
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.
- 5d ago First seen · 44 lines · 0 tokens per session scan A 32e16aa6545f
headless-development is an agent published in the GitHub repository praveenjuge/teak (25 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. 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 agents, from other repositories
Marketing Report Builder
Agent "Marketing Report Builder" from muratgur/ordinus, covering role, capabilities, requested work, instructions and marketing report builder.
reviewer
Code review, debug complesso e QA - analisi cause radice, regressioni, verifica pre-deploy. Usalo per rivedere lavoro fatto o inchiodare bug.
action-library-search
Search installed actions and read exemplar programs for learning (read-only).
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.
curator
Reads one repository and returns its five knowledge documents as text. Read-only by construction — it cannot write files. Use it for /study, /refresh, and any time a repo needs to be understood from scratch.
trellis-research
Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.