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 skills add Justinmendezai/The-Adam-Repo --skill dev-launch-debuggit clone --depth 1 https://github.com/Justinmendezai/The-Adam-RepoWrote 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/skills/justinmendezai/the-adam-repo/dev-launch-debug)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/dev-launch-debug"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/dev-launch-debug/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/skills/justinmendezai/the-adam-repo/dev-launch-debug"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/dev-launch-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02181 |
| Opus 5 | $0.00038 | $0.01091 |
| Sonnet 5 | $0.00015 | $0.00436 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
dev-launch-debug scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Pasting CLI for the operator to run when you could execute it yourself (install, migrate, curl, restart server). How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-launch-debug
The "make the app run end-to-end first, clean up later" skill. Distinct from diagnose: diagnose is for hard bugs of unknown root cause; this skill is for "the app is broken end-to-end on a fresh checkout and we need it green to start work." Distinct from e2e-acceptance: e2e-acceptance is the final integration gate; this is the first gate.
Core rule
Full E2E path completion beats clean fixes.
You are a path-unblocker, not a refactor agent. Every decision flows from that.
Rules
- Do not refactor unless required to unblock the path.
- Do not chase non-blocking warnings.
- Do not fix unrelated issues you happen to notice.
- Use logs, browser console, network tab, and server traces before guessing.
- Every blocker gets recorded in the ledger before you start fixing it.
- If a fix is risky or scope-creeping, write the issue to the ledger and move on unless it blocks E2E.
- Keep the app runnable after every change. If a change breaks the boot, revert before continuing.
- One fix per retest. Batching fixes hides which one worked.
When to use
- Fresh clone or
npm install/pip installon a teammate's machine; nothing works yet. - Post-merge dev launch is red.
- A subagent left main on a half-working state and a human needs to bring it back to green before slicing more work.
- You catch yourself about to "just refactor this real quick" while the happy path is still broken.
When NOT to use
- A single test is failing in CI but the app launches fine → use
diagnose. - All slices are merged and you are doing the final gate → use
e2e-acceptance. - You are writing a new feature → use
tdd.
Workflow
1. Identify the target path
Open agent-control/dev-launch-ledger.md (seeded by adam-foundation-sync). Fill in the Current Target Path block:
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 · 178 lines · 76 tokens per session scan A 8ab3c8fb1fde
dev-launch-debug is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 76 tokens to every session and 2,181 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.