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 commands/nnhhoang/claude-engineering-coach/summarygit clone --depth 1 https://github.com/nnhhoang/claude-engineering-coachWrote 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/commands/nnhhoang/claude-engineering-coach/summary)<a href="https://agentmods.dev/commands/nnhhoang/claude-engineering-coach/summary"><img src="https://agentmods.dev/badge/commands/nnhhoang/claude-engineering-coach/summary.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 5.1 | $0.00017 | $0.00172 |
| Opus 5 | $0.00009 | $0.00086 |
| Sonnet 5 | $0.00003 | $0.00034 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
summary 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
Call the coach_summary tool from the AI Engineering Coach MCP server to fetch the user's usage summary.
- If
$ARGUMENTScontains one or two ISO dates, pass them asfromDate/toDate. Otherwise let the tool default to the last 90 days. - Then present, concisely and terminal-friendly:
- Total sessions and the per-harness breakdown (highlight Claude Code).
- AI vs human lines of code.
- The top 3 anti-patterns, each with one concrete improvement.
End with a one-line suggestion to run /coach:improve for detail.
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 · 15 lines · 17 tokens per session scan A a06cb6e0cac0
summary is a command published in the GitHub repository nnhhoang/claude-engineering-coach (1 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 172 once invoked, about $0.0001 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 commands, from other repositories
ticket
Take a GitHub issue through an isolated implementation and pull request in its own Herdr tab.
spec
Generate a specification for AI-assisted implementation.
review
Command "review" from owainlewis/youtube-tutorials, covering review, target, instructions, simplicity and clarity.
command-template.claude
Command "command-template.claude" from Enovatr-Labs/SpecRoute, covering what this command does, implementation, inline shell commands the slash command runs, output and when to use.
status
Report the current state of the SpecRoute skeleton - which top-level dirs exist, which artifacts have been drafted, what's outstanding.
feature-full
Full feature pipeline — runs /distill → /howto-implement → /verify(IMP) → /trace(virtual) → ASK USER → /implement → /trace(real) → /verify(impl) sequentially. Triggers: /feature-full, "full feature pipeline", "spec to code", "implement this story end-to-end", Jira user story / requirement wanting entire pipeline.…