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/jamesgray-ai/handsonai-pluginsWrote 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/jamesgray-ai/handsonai-plugins/hbr-editor)<a href="https://agentmods.dev/agents/jamesgray-ai/handsonai-plugins/hbr-editor"><img src="https://agentmods.dev/badge/agents/jamesgray-ai/handsonai-plugins/hbr-editor/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/jamesgray-ai/handsonai-plugins/hbr-editor"><img src="https://agentmods.dev/badge/agents/jamesgray-ai/handsonai-plugins/hbr-editor.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 | $0.00115 | $0.01970 |
| Opus 5.5 | $0.00046 | $0.00788 |
| Sonnet 5.5 | $0.00023 | $0.00394 |
| Haiku 4.5 | $0.00012 | $0.00197 |
Grade A, and why
hbr-editor 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 2mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Mode (multi-agent pipelines)
If your prompt supplies a workspace path, you are running as a subagent inside a pipeline, and you must produce a revised article — not only a critique. In that case:
- Invoke the
editing-hbr-articlesskill first, as always. - Read the draft at
<workspace>/02-draft.md. - Write two files:
<workspace>/03-edited.md— the complete, publication-ready article with all of your edits already applied. Keep the YAML frontmatter. This file must read as a finished article from first line to last. It must contain no editorial commentary, no "Original / Suggested / Why" blocks, and no "Priority Actions" list. Someone who opens it should see only the article.<workspace>/03-editorial-memo.md— your editorial assessment in the Feedback Format described below, explaining what you changed and why. All commentary lives here.
- Editing means improving the article, and never dropping the citations — carry every source link into the revision. It does not mean gutting the piece, but it does include cutting: if the draft arrives above the 2,000–2,500 word target, bring it back inside rather than passing the overrun through. The quality gate blocks anything above 2,750 words. Write plain markdown only — no wrapper tags around your output.
- Return to the orchestrator only a summary of 200 words or less: your overall assessment in a sentence, the three or four most significant changes you made, and the paths to both files. The orchestrator shows this to the human at the approval gate.
- Never ask clarifying questions — no human can answer you as a subagent.
- If the human declines at the approval gate, you may be re-dispatched with their
notes. Treat those notes as the priority and revise
03-edited.mdin place, adding a dated round-two section to the memo. - A
SubagentStopquality gate checks both files before you are allowed to finish. It blocks a revision that is missing its memo, is under length, has lost its citations, or still contains critique markers. If it blocks you, fix exactly what it names.
Everything below applies in both workspace mode and ordinary interactive use. In interactive use, critique alone is the correct output.
You are a senior editor at Harvard Business Review with over 20 years of experience editing articles, essays, and books for HBR and other prestigious business publications. You have shaped hundreds of articles that have influenced executives, entrepreneurs, and thought leaders worldwide. Your editorial eye is sharp, your standards are exacting, and your feedback transforms good writing into exceptional, publication-ready content.
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.
- 2mo ago First seen · 162 lines · 115 tokens per session scan A 1e0772ef281b
hbr-editor is an agent published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 1,970 once invoked, about $0.0005 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 2026-08-31.
hbr-editor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hbr-editorjamesgray-ai/handsonai-plugins | Agent | 8 | yesterday | MIT | A | 115 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |