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 skills/bananasjim/openplan-skill/openplan-html-briefnpx skills add BANANASJIM/openplan-skill --skill openplan-html-briefgit clone --depth 1 https://github.com/BANANASJIM/openplan-skillWrote 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/bananasjim/openplan-skill/openplan-html-brief)<a href="https://agentmods.dev/skills/bananasjim/openplan-skill/openplan-html-brief"><img src="https://agentmods.dev/badge/skills/bananasjim/openplan-skill/openplan-html-brief.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 | $0.00090 | $0.01267 |
| Opus 5 | $0.00045 | $0.00633 |
| Sonnet 5 | $0.00018 | $0.00253 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
openplan-html-brief 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPlan HTML Brief
Use this as a better temporary frontend for human understanding. It turns agent output into a concise, readable HTML page.
Default Behavior
- Generate a single self-contained
.htmlfile. - Default location:
/tmp/openplan-brief-<timestamp>.html. - Do not add it to git.
- Do not place it in the project repo unless the user explicitly asks.
- Do not make it the source of truth. It is a visual summary over durable artifacts.
- If file writing is unavailable, return the HTML in a fenced code block.
Good Uses
- Summarize what an agent did.
- Present auto-review findings.
- Teach a project concept visually.
- Show a handoff snapshot to a human.
- Compare goal/intent/design/spec/code surfaces.
- Explain next safe actions and human decisions.
Page Shape
Keep it simple:
- Header: title, timestamp, scope.
- Status strip: mode, result, risk level, human decision needed.
- Main summary: 3-6 bullets.
- Evidence cards: paths, commands, reports, or missing artifacts.
- Findings or lessons: grouped by severity or topic.
- Human decisions: explicit non-automated decisions.
- Next safe action.
- Residual risk.
Frontend Rules
- Use plain HTML/CSS/JS only.
- Inline CSS; avoid external CDN dependencies.
- Responsive layout, readable on laptop and mobile.
- No heavy decoration, no marketing hero, no gradients unless useful for status.
- Prefer tables for comparisons, cards for repeated findings, and callouts for decisions/blockers.
- Keep text concise; do not dump raw logs.
- Escape user/file content before embedding.
- Do not include secrets or credentials.
Visual Semantics
Use calm status colors:
- green: no blocking findings;
- amber: attention or uncertainty;
- red: blocked/P0/P1;
- blue/gray: informational.
Do not let color be the only signal; include text labels.
Minimal Template
<!doctype html>
<html lang="en">
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>OpenPlan Brief</title>
<style>
:root { color-scheme: light; font-family: Inter, ui-sans-serif, system-ui, sans-serif; }
body { margin: 0; background: #f6f7f9; color: #1f2937; }
main { max-width: 1080px; margin: 0 auto; padding: 28px; }
header { margin-bottom: 18px; }
h1 { margin: 0 0 6px; font-size: 28px; letter-spacing: 0; }
h2 { margin: 22px 0 10px; font-size: 18px; }
.meta { color: #667085; font-size: 14px; }
.strip { display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 10px; }
.tile, .card { background: white; border: 1px solid #e5e7eb; border-radius: 8px; padding: 14px; }
.label { color: #667085; font-size: 12px; text-transform: uppercase; letter-spacing: .04em; }
.value { margin-top: 4px; font-weight: 650; }
.ok { border-left: 4px solid #16a34a; }
.warn { border-left: 4px solid #d97706; }
.bad { border-left: 4px solid #dc2626; }
ul { padding-left: 20px; }
code { background: #f2f4f7; padding: 2px 5px; border-radius: 4px; }
table { width: 100%; border-collapse: collapse; background: white; border: 1px solid #e5e7eb; }
th, td { text-align: left; padding: 10px; border-bottom: 1px solid #e5e7eb; vertical-align: top; }
th { background: #f9fafb; font-size: 13px; color: #475467; }
</style>
<main>
<header>
<h1>OpenPlan Brief</h1>
<div class="meta">Scope: ... · Generated: ...</div>
</header>
<section class="strip">
<div class="tile"><div class="label">Mode</div><div class="value">Review</div></div>
<div class="tile"><div class="label">Result</div><div class="value">No blocking findings</div></div>
<div class="tile warn"><div class="label">Human Decision</div><div class="value">Needed</div></div>
</section>
<section>
<h2>Summary</h2>
<div class="card"><ul><li>...</li></ul></div>
</section>
</main>
</html>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 115 lines · 90 tokens per session scan A d18f131f2770
openplan-html-brief is a skill published in the GitHub repository BANANASJIM/openplan-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,267 once invoked, about $0.0005 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 skills, from other repositories
nhk-bootstrap
Bootstrap an NHK workspace when first-time setup is needed or any required instruction, routing, planning, governance, or archive surface is missing.
nhk-archive
Archive one completed NHK workstream when the human has explicitly approved its active-to-archive transition.
nhk-upkeep
Repair NHK drift when an established workspace's instruction, routing, planning, governance, archive index, or tracking descriptions no longer match reality.
welcome-to-nhk
Route NHK work when dependency readiness, instruction topology, foundation state, or lifecycle stage is unresolved.
scribe-integration
How to use Scribe MCP tools correctly — logging, docs, topology, bugs, file reading, search.
scribe-onboarding
Install and connect Scribe MCP — pip install, one-command Postgres bootstrap, host/plugin projection, and first-bind verification.