Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bolnet/attestornpx agentmods add commands/bolnet/attestor/demo-recordingWrote 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/bolnet/attestor/demo-recording)<a href="https://agentmods.dev/commands/bolnet/attestor/demo-recording"><img src="https://agentmods.dev/badge/commands/bolnet/attestor/demo-recording.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 | $0.00014 | $0.01785 |
| Opus 5 | $0.00007 | $0.00892 |
| Sonnet 5 | $0.00003 | $0.00357 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
demo-recording 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 8d 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 -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8080/ui/memories How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record Attestor UI Demo
Record a comprehensive demo walkthrough of the Attestor UI — a screen-recorded video that explores every page, every interactive element, every sub-menu, input field, and animation. Then generate a timestamped voiceover script the user can read for narration.
Prerequisites
- Attestor UI must be running:
attestor ui --path <store>on port 8080 - Store should have 20+ seeded memories across multiple entities/namespaces
- Node.js +
playwrightnpm package installed (npm install playwright)
Step 1 — Verify Server
curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8080/ui/memories
If not 200, tell the user to start the server.
Step 2 — Run the Recording Script
The recording script lives at docs/demo/record-demo.js. Run it:
node docs/demo/record-demo.js
Then rename the output:
# Find the auto-generated webm and rename
mv docs/demo/page@*.webm docs/demo/ui-walkthrough.webm
What the Script Records (18 Screens)
The script navigates every page and interacts with every element. Here is the full sequence — if the script needs updating, follow this exact interaction order:
| # | Page | Interactions | Duration |
|---|---|---|---|
| 01 | Evidence Board | Land, watch card stagger animation, scroll down and back | 5s |
| 02 | Search | Type "architecture" in search, watch HTMX live filter + highlights, scroll | 5s |
| 03 | Namespace filter | Clear search, type "default" in namespace field | 3s |
| 04 | Status filter | Switch to "superseded", then back to "active" | 4s |
| 05 | Clear filters | Navigate fresh to /ui/memories |
2s |
| 06 | Card hover | Hover 2 cards to show lift animation | 2s |
| 07 | Memory dossier | Click first card, scroll detail page | 4s |
| 08 | Dossier tabs | Click all 6 tabs: provenance → supersession → embedding → graph → access → content, scroll each | 12s |
| 09 | Knowledge graph | Land, click 2 nodes, show inspector panel | 7s |
| 10 | Graph controls | Search "Attestor", switch layouts (concentric → circle → cose), change sizing (pagerank → degree), fit view | 12s |
| 11 | Recall pipeline | Type query, set budget, execute, watch 5-layer animation, scroll results | 8s |
| 12 | Budget explorer | Click Budget Explorer, wait for 5-budget comparison, scroll chart | 8s |
| 13 | Timeline | Auto-load, scroll, click card → detail slide-in, close, filter superseded, reset | 12s |
| 14 | Agents | Auto-load, scroll, click namespace card → detail overlay, scroll inside, close | 10s |
| 15 | Health | Land, scroll to see all 4 component cards + percentiles + sparkline | 5s |
| 16 | Config | Land, scroll all config sections | 5s |
| 17 | Ops log | Land, scroll flight recorder table | 5s |
| 18 | Theme toggle | Switch dark → light, scroll in light mode, switch back to dark | 7s |
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.
- 8d ago First seen · 174 lines · 14 tokens per session scan A 83bc8576e973
demo-recording is a command published in the GitHub repository bolnet/attestor (14 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 1,785 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
pn-quieter
Reduce visual decoration — animations, colors, shadows, effects — without removing content. Use when there's too much visual noise. For content and feature reduction, use pn-distill.
video
Route work to the Video primary agent.
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
add-to-context
Promote reviewed journal facts into context/project/ (propose, then apply).
cwb-relax
A command that searches for relaxing music in three styles: downtempo, acoustic folk, and nature ambience.
station
You are helping the user work with Station - the self-hosted AI agent orchestration platform.