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 grburgess/mindgap --skill live-viewgit clone --depth 1 https://github.com/grburgess/mindgapWrote 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/grburgess/mindgap/live-view)<a href="https://agentmods.dev/skills/grburgess/mindgap/live-view"><img src="https://agentmods.dev/badge/skills/grburgess/mindgap/live-view/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/grburgess/mindgap/live-view"><img src="https://agentmods.dev/badge/skills/grburgess/mindgap/live-view.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 | $0.00126 | $0.02244 |
| Opus 5.5 | $0.00050 | $0.00898 |
| Sonnet 5.5 | $0.00025 | $0.00449 |
| Haiku 4.5 | $0.00013 | $0.00224 |
Grade A, and why
live-view scanned grade A with 1 finding 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf localhost:8765/api/runs >/dev/null || echo "need server" How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
live-view
A per-run page at http://localhost:<port>/runs/<run-id>, served by mindgap serve
from ~/.mindgap/runs/<run-id>/. The page is a fixed shell (hero status + go/no-go,
stat tiles, the court = agents by phase, decisions feed, questions) plus optional
bespoke panels the page-builder writes for THIS task. The user can ask about any
agent/decision, contest it, and answer your questions from the page. Data never leaves
the laptop.
Every page also gets three animated diagrams for free (web/run-viz.js): a pulse card
(progress ring, verdict-mix bar, working/elapsed), the court map (claims → lens agents →
ruling → decision; particles flow into working agents, nodes pop into their verdict colour)
and a timeline (one growing bar per agent + markers for rulings, questions, contests).
They key off agent labels <lens>:<subject>, claim events (subject = the same id) and
ruling/decision events — emit those and the diagrams draw themselves.
You are the only writer of semantic events. Workflow scripts cannot write files, so the
page reads per-agent progress passively from the Workflow's transcript dir once you
bind it — you never emit per-agent events yourself.
Protocol
1 · Start (before the first fan-out)
curl -sf localhost:8765/api/runs >/dev/null || echo "need server"
need server+ port free → startmindgap serve --no-openin the background (Bashrun_in_background). Port 8765 held by a server WITHOUT/api/runs= an old process → don't kill it; serve on--port 8777and use that port in the URL.mindgap run start --skill <skill> --title "<what is being decided>" [--port N]→ prints the run id + URL. Give the user the URL in your next message. WithMINDGAP_BROWSER=itermit also opens the page in an iTerm2 split pane beside this session — still give the URL.- Arm the back-channel: Bash with
run_in_background: truerunningmindgap run inbox <run-id> --once. It blocks silently until the page posts, prints that burst (one JSON message per line) and exits — you are notified exactly then, never on a timer. Reply to EVERY line, then re-arm the same command at once. It resumes from a saved cursor, so anything posted while it was down arrives on re-arm, each message exactly once. Do NOT use aMonitorfor this: a Monitor expires every ≤30 min and each expiry wakes you for nothing (a real loop session logged 29 empty expiries).
What ships with it
3 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.
- 23d ago Changed · +1 lines 6def0d7b1dc6
- 27d ago First seen · 117 lines · 126 tokens per session scan A 6cdbfa485dd3
live-view is a skill published in the GitHub repository grburgess/mindgap (0 stars, last pushed 23d ago), licensed MIT. It adds 126 tokens to every session and 2,244 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
live-view compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| live-viewgrburgess/mindgap | Skill | 0 | 23d ago | MIT | A | 126 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |