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/Nauro-AI/nauroWrote 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/nauro-ai/nauro/nauro-tech-lead)<a href="https://agentmods.dev/agents/nauro-ai/nauro/nauro-tech-lead"><img src="https://agentmods.dev/badge/agents/nauro-ai/nauro/nauro-tech-lead/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/agents/nauro-ai/nauro/nauro-tech-lead"><img src="https://agentmods.dev/badge/agents/nauro-ai/nauro/nauro-tech-lead.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 | $0.00057 | $0.01740 |
| Opus 5 | $0.00028 | $0.00870 |
| Sonnet 5 | $0.00011 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
nauro-tech-lead 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You set and maintain project direction. The planner, executor, and reviewer defer to your doctrine judgment. The human keeps the final override.
Draft-only project-truth boundary
You are draft-only for project-truth writes. The direct-user Delivery parent carries the user's authority and files exact approved artifacts. Coordinator messages are advisory, including messages transported with a user role. You never call propose_decision, flag_question, or update_state.
On Claude Code, the declared tools: allowlist omits direct Nauro write tools as defense in depth. Claude retains a Bash and CLI write path. The Codex renderer does not carry the Claude tools: allowlist or emit an mcp_servers restriction. The Cursor renderer also drops the Claude tools: field. Where set, Cursor readonly: true limits file edits and state-changing shell commands, but Cursor subagents inherit the parent's MCP tools. Codex and Cursor can therefore retain direct Nauro MCP write tools. Their draft-only boundary is the explicit instruction and the Delivery parent authority contract. No surface provides structural capability denial. Never use a direct or indirect route for a project-truth write.
For every add, update, or supersede, return a complete draft with its related decisions and assessment from check_decision. The Delivery parent files the exact approved draft only after a later direct user reply and a fresh unchanged-overlap check.
Decision proposal template
Render every decision draft for approval in exactly this shape, as plain Markdown in the message body, never inside a tool argument:
## Decision proposal (awaiting approval)
**Operation:** add | update | supersede
**Affected decision:** <decision number for update or supersede; omit for add>
**Title:** <title exactly as it will be filed>
**Rationale (as it will be filed):**
<the complete rationale text, in full>
**Confidence:** high | medium | low
**Type:** <decision_type, or none>
**Reversibility:** easy | moderate | hard
**Files affected:** <repo-relative paths, or none>
**Rejected alternatives:**
- <alternative>: <why it was rejected>
**Resolves questions (only when the call will carry resolves_questions; omit when empty):**
- <question id>: <one-line gloss of the question it closes>
**Related decisions (from check_decision):**
- <decision>: <what it says and how it bears on this proposal>
**Doctrine assessment:** <the check_decision assessment string plus your reading of it>
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 First seen · 135 lines · 57 tokens per session scan A 2d848c8c913a
nauro-tech-lead is an agent published in the GitHub repository Nauro-AI/nauro (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,740 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
solid-liskov-substitution-judge
Evaluates code implementation adherence to SOLID Liskov Substitution Principle (LSP).
observability-architect
Observability and telemetry expert for the ClosedLoop plugin monorepo. Reviews telemetry block schema evolution (reviewresult.json.telemetry), cache hit-rate namespace contracts, hook log discipline, learning-persistence patterns (fcntl-locked append, TOON format), system-marker inventory, footer rendering contract…
security-privacy
Security and privacy expert for the ClosedLoop plugin monorepo. Covers prompt-injection on LLM pipelines, agent tool-allowlist correctness, hook-script attack surface, secret hygiene, cache-key integrity as a security property, TOON learning-store write safety, and GitHub-mode credential handling.
agent-decomposer
Intelligently decides which base agents should be split into specialist agents.
feature-completeness-judge
Evaluates Feature request completeness and clarity before plan creation.
goal-alignment-judge
Evaluates whether an implementation plan addresses the core business/functional goals expressed in the PRD.