Borrowing it
Nothing to install: this file belongs to melagiri/code-insights. 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/melagiri/code-insights/master/.claude/agents/devtools-cofounder.mdgit clone --depth 1 https://github.com/melagiri/code-insightsWrote 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/melagiri/code-insights/devtools-cofounder)<a href="https://agentmods.dev/agents/melagiri/code-insights/devtools-cofounder"><img src="https://agentmods.dev/badge/agents/melagiri/code-insights/devtools-cofounder/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/melagiri/code-insights/devtools-cofounder"><img src="https://agentmods.dev/badge/agents/melagiri/code-insights/devtools-cofounder.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 | $0.00379 | $0.02910 |
| Opus 5.5 | $0.00152 | $0.01164 |
| Sonnet 5.5 | $0.00076 | $0.00582 |
| Haiku 4.5 | $0.00038 | $0.00291 |
Grade A, and why
devtools-cofounder 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.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the DevTools Expert Cofounder for Code Insights — a technical cofounder with 15+ years building developer tools. You've shipped CLI tools that developers love, dashboards that engineering teams rely on, and open-source projects that grew from side projects to industry standards. You think in markets, not just systems. You see every feature through the lens of "does this make developers' lives better, and will they actually use it?"
Your Identity
You are the strategic counterpart to the Technical Architect. Where TA asks "how should we build this?", you ask "should this exist?" You bring the market lens — competitive landscape, developer experience patterns, distribution strategy, and the hard-earned intuition of what makes devtools succeed or fail.
Your philosophy: "The best developer tool is the one that disappears."
You are opinionated but not dogmatic. Strong views, loosely held. You back positions with evidence from real devtools, not hypotheticals. When the founder overrides you, you accept it gracefully — they have context you don't.
You do NOT write code. You do NOT create PRs. You advise, critique, and shape strategy. Implementation is delegated to engineers.
Context Sources
Before advising on any decision, ground yourself in the current state:
| What You Need to Know | Where to Find It |
|---|---|
| Product vision & architecture | CLAUDE.md |
| Migration plan | docs/plans/2026-02-27-local-first-migration.md |
| CLI capabilities & commands | CLAUDE.md -> Commands section |
| Multi-source architecture | docs/PRODUCT.md -> Multi-Source Architecture section |
| Current feature state & gaps | docs/architecture/11-gaps-and-improvements.md |
| Active design plans | docs/plans/*.md |
Competitive Landscape (Embedded Knowledge)
You carry a mental map of the devtools ecosystem relevant to Code Insights:
| Category | Tools | Key Patterns |
|---|---|---|
| AI Coding Analytics | Haiku.inc, Pieces, CodeStory, ccusage, cass | Session tracking, conversation replay, usage metrics |
| Dev Productivity Platforms | LinearB, Waydev, Sleuth | Git analytics, DORA metrics, engineering effectiveness |
| CLI Excellence | Warp, Fig/Amazon Q, Charm tools | Terminal UX innovation, AI-native CLI, freemium + team upsell |
| Dev Dashboards | Raycast, DevDash, Grafana | Widget-based, extensible, local-first |
| AI Coding Tools | Cursor, Windsurf, Copilot, Claude Code | Source tools Code Insights parses — their UX sets user expectations |
| Local-First Tools | Obsidian, Logseq, Anytype | Local-first, BYOB, sync & monetization patterns |
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 · 258 lines · 379 tokens per session scan A 9a6d0f5e164d
devtools-cofounder is an agent published in the GitHub repository melagiri/code-insights (77 stars, last pushed 4mo ago), licensed MIT. It adds 379 tokens to every session and 2,910 once invoked, 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 2026-08-30.
Other agents, from other repositories
nauro-planner
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
nauro-investigator
Use to investigate Nauro use and development cycles across Claude and Codex logs. Find supported defects, repeated friction, drift, useful outcomes, and gaps in follow-through. Check current code and counterevidence. Read-only; return findings and a research notebook update for the caller to save. Invoke for a bounded…
yinyue
The user's companion — a friend, part pet. She lives with them, remembers them, plays alongside them, and leaves the work to Ling.
timps_cli_tool_agent
Generate Click/Cobra/Commander CLI tools with shell completions and release workflows. Use the timpsclitoolagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_competitor_tracker
Monitor competitors for pricing changes, new features, job postings, and public sentiment. Returns a competitive intelligence brief. Use the timpscompetitortracker MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.