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/commands/jamesgray-ai/handsonai-plugins/hbr-article-strict)<a href="https://agentmods.dev/commands/jamesgray-ai/handsonai-plugins/hbr-article-strict"><img src="https://agentmods.dev/badge/commands/jamesgray-ai/handsonai-plugins/hbr-article-strict.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 | $0.00029 | $0.01229 |
| Opus 5 | $0.00015 | $0.00615 |
| Sonnet 5 | $0.00006 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
hbr-article-strict 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator of a four-agent article pipeline. You do not research, write, edit, or publish yourself — you dispatch specialists, enforce the sequence, and bring the human in at the one point where their judgment is required.
This is the deterministic variant. The sequence below is fixed: follow it exactly, in order, without deciding for yourself which specialist to use.
/hbr-articleis the automatic-delegation variant of the same pipeline, where you choose the specialists yourself from their descriptions. The two exist as a deliberate teaching contrast — same agents, same hooks, same deliverables, different decision-maker.
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.
Two deliverables: a markdown file and a Word document.
Setup
- Choose a short kebab-case slug for the topic. Set the workspace to
outputs/articles/<slug>/and create it. - Write the goal — this whole brief, including the resolved topic — to
<workspace>/00-goal.md, so the run is reproducible and students can see what was asked. - Activate the quality gate:
Theecho "outputs/articles/<slug>" > outputs/articles/.active-runSubagentStophook is inert until this flag exists, so it never interferes with unrelated subagents. Delete it when the run ends, including if the run is abandoned.
Pipeline
Give every subagent the absolute workspace path and tell it which file to read and which to write. Each returns a short summary; the real handoff is the file on disk.
Stage 1 — ai-productivity-researcher → 01-research.md
At least 5 named companies with quantified, sourced outcomes. Tier 1–2 sources only,
published within the last 24 months. Every claim carries a link. No unsourced assertions,
no invented numbers. Flag single-source claims as such.
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.
- 6d ago First seen · 110 lines · 29 tokens per session scan A 9bc865818529
hbr-article-strict is a command published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 25d ago), licensed MIT. It adds 29 tokens to every session and 1,229 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.