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/jamesgray-ai/handsonai-plugins/hbr-articlegit 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/commands/jamesgray-ai/handsonai-plugins/hbr-article)<a href="https://agentmods.dev/commands/jamesgray-ai/handsonai-plugins/hbr-article"><img src="https://agentmods.dev/badge/commands/jamesgray-ai/handsonai-plugins/hbr-article.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 | $0.00017 | $0.01184 |
| Opus 5 | $0.00009 | $0.00592 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
hbr-article 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Produce a Harvard Business Review–style article, for a senior business leadership audience, on: $1
If $1 is empty, the topic is: companies that have successfully deployed AI agents in
their business, and what separated them from the ones still running pilots.
Done means two files exist on disk: the article as markdown, and the article as a Word document. Publication quality, and defensible — every factual claim traceable to a credible, cited source.
How to approach this
You have specialist subagents available, and you decide which to use and when. This is deliberate: read the available agent descriptions, work out which specialists this goal calls for, and delegate to them in whatever order the work requires. Nobody is handing you a sequence.
Three rules constrain how you delegate, not what you choose:
- Do not do a specialist's work yourself. If a specialist exists for a part of this goal, dispatch it rather than doing that part in your own context. This is the whole point — you are coordinating experts, not doing the job with help. Notably: do not research the case studies yourself, and do not write or edit the prose yourself.
- Every handoff goes through a file, and every subagent gets the absolute workspace path. Subagents cannot see your context or each other's. If you don't tell an agent where to read from and write to, the chain breaks.
- Keep your own context clean. Subagents return short summaries plus paths by design. Don't pull whole dossiers or drafts into your context; read a specific file only when you need a specific passage.
Workspace
- Choose a short kebab-case slug for the topic. Create
outputs/articles/<slug>/. - Write this brief, with the resolved topic, to
<workspace>/00-goal.md. - Arm the quality gates:
The hooks are inert until this flag exists. Remove it when the run ends, including if you abandon the run.echo "outputs/articles/<slug>" > outputs/articles/.active-run
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 · 109 lines · 17 tokens per session scan A 65f1196c4aa3
hbr-article is a command published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 24d ago), licensed MIT. It adds 17 tokens to every session and 1,184 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.