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 NOMARJ/sigil --skill hmw-generatorgit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/hmw-generator)<a href="https://agentmods.dev/skills/nomarj/sigil/hmw-generator"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/hmw-generator/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/nomarj/sigil/hmw-generator"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/hmw-generator.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 | $0.00071 | $0.01075 |
| Opus 5.5 | $0.00028 | $0.00430 |
| Sonnet 5.5 | $0.00014 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
hmw-generator 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HMW Generator — From Understanding to Opportunity
Purpose
"How Might We" is IDEO's single highest-leverage method. It is the bridge between "I understand the problem" and "I'm generating solutions." It encodes the person into the solution prompt itself, preventing solutioning that ignores the human or agent consumer.
A well-framed HMW invites multiple solutions. A badly-framed one either constrains too early (implies a solution) or expands too far (provides no traction).
Input
One of:
- An insight statement from the Insight Registry:
INS-XXX: [Who] needs [what] because [why] - A raw problem description:
"Users struggle with..." - A persona frustration from a synthetic interview transcript
Process
1. Extract the Core Elements
From the input, identify:
- Who — the specific person or agent type
- Need — what they're trying to accomplish
- Barrier — what prevents them
- Context — circumstances that shape the problem
2. Generate Variants at Different Scopes
| Scope | Template | Example |
|---|---|---|
| Systemic | HMW change the system so [who] doesn't face [barrier]? | HMW redesign the onboarding flow so new users don't need to read documentation? |
| Experience | HMW make [activity] feel [desired state] for [who]? | HMW make account setup feel effortless for non-technical users? |
| Friction | HMW remove [specific friction] from [who]'s [activity]? | HMW eliminate the 6-step verification process for returning users? |
| Reframe | HMW turn [barrier] into an advantage for [who]? | HMW use the mandatory compliance step as a trust signal? |
| Inversion | HMW prevent [who] from ever experiencing [pain]? | HMW ensure users never see an error page during checkout? |
3. Scope Test Each Variant
For each HMW, apply the IDEO scope test:
- Too broad? Can you generate 5 solutions in 2 minutes? If not → narrow it
- Too narrow? Does it imply only one solution? If yes → broaden it
- Implies a solution? Does it contain a feature name or technology? If yes → remove it and reframe as need
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.
- 1mo ago First seen · 103 lines · 71 tokens per session scan A f8799778f11d
hmw-generator is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,075 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
sftp-cc
A natural-language SFTP tool for uploading local project files to a remote server. SFTP is a secure way to transfer files, and this tool supports incremental uploads, private-key binding, and permission fixes.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
thread-list
Inspect or change the sidebar thread list's layout preferences: organization mode, sort, section order, hidden groups, collapsed groups, and thread row actions.
workflows
Author or run durable BB workflows when the user requests workflow execution or multi-agent orchestration.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
url
Fetch and extract text from web URLs.