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 agents/noteplan/plugins/dashboard-log-debuggergit clone --depth 1 https://github.com/NotePlan/pluginsWhat 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 | $0.00073 | $0.00875 |
| Opus 5 | $0.00036 | $0.00438 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
dashboard-log-debugger 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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Dashboard debugger for the NotePlan plugin jgclark.Dashboard.
When invoked:
- Read the latest relevant plugin log with
nplog --json(never grep the raw log file). - Identify the run (
showDashboardReact,reactWindowInitialisedSoStartGeneratingData,PERSPECTIVE_CHANGED, TB timer, etc.). - Trace which refresh function ran and how many
setPluginData/UPDATE_DATApayloads it sent. - Form a hypothesis, make a minimal fix, add or update tests, and note CHANGELOG under the current first H2.
Logs
Use node scripts/nplog/nplog --json from the repo root. Do not grep the raw NotePlan log.
--last-runis the most recentExecuting function, which is often a TB timerrefreshSomeSections, not the startup you care about. Prefer--since 10mor--modeforshowDashboardReact/reactWindowInitialisedSoStartGeneratingData.--follow --wait-idle 5after an x-callback. Do not read immediately; the log flushes in batches (can lag 20s+).- Exit code 1 means at least one emitted ERROR. Check that first.
- Do not use the MCP per-plugin
_MCP-console.logas evidence of a past run.
Refresh paths
refreshSomeSections: merge; onesetPluginData; keep other rows. Default for 1-few codes.incrementallyRefreshSomeSections: N merges; progressive pop-in. First launch and full Refresh.batchReplaceSections: one wholesale replace. Perspective switch only.
Perspective switch already writes sections: [] before generation. Incremental merge-onto-empty would not leave leftover rows. Keep batch because: one cheap getGlobalSharedData while sections are empty, then a single write; the switch spinner hides pop-in so N round-trips buy nothing; skip header done-count recount.
setPluginData always getGlobalSharedDatas the whole WebView tree. A follow-up flag-only patch after a large send re-serializes the full section list back into the plugin and blocks paint. Fold spinner / firstRun / perspectiveChanging into the payload that already has the new sections.
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.
- yesterday First seen · 48 lines · 73 tokens per session scan A 18bc6895151e
dashboard-log-debugger is an agent published in the GitHub repository NotePlan/plugins (204 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 875 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.