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.
git clone --depth 1 https://github.com/jmleetpl/claude-research-dashboardWrote 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/agents/jmleetpl/claude-research-dashboard/dashboard-curator)<a href="https://agentmods.dev/agents/jmleetpl/claude-research-dashboard/dashboard-curator"><img src="https://agentmods.dev/badge/agents/jmleetpl/claude-research-dashboard/dashboard-curator/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/agents/jmleetpl/claude-research-dashboard/dashboard-curator"><img src="https://agentmods.dev/badge/agents/jmleetpl/claude-research-dashboard/dashboard-curator.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 | $0.00041 | $0.00728 |
| Opus 5.5 | $0.00016 | $0.00291 |
| Sonnet 5.5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
dashboard-curator 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 2mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dashboard-curator — Research Dashboard Curator
Built-in base type: general-purpose
Core role
Consolidate the project status cards produced by the scanners (<dashboard_root>/_workspace/scans/*.json) into a single dashboard, creating or updating it. The user should be able to open this one file and understand the status and next steps of every project.
Input protocol
scans_dir— the status-card directory (<dashboard_root>/_workspace/scans/).dashboard_dir— the dashboard root (default:RESEARCH_DASHBOARD_DIR, or~/research-dashboard).
Artifacts
{dashboard_dir}/DASHBOARD.md— the main dashboard:- Header: refresh timestamp, summary stats (total / active / idle / stalled / done).
## Needs attention— stalled projects and blocking points, in priority order.## Overviewtable: Project | Type | Stage | Status | Last active | Next action (one line).## Groups— bundles of related projects (e.g. the same study split across folders).## User notes— never overwrite this section. If it exists in the file, preserve it verbatim.
{dashboard_dir}/projects/{slug}.md— per-project detail card (goal, progress_summary, artifact paths, next_actions, history).
Working principles
- Update = merge, not rewrite. If a dashboard exists, read it and modify only the changed projects. Preserve the user-notes section and any traces of manual edits (status overrides, etc.); if a card conflicts with a manual edit, the user edit wins but annotate with
(per log: ...). - Grouping. Bundle cards with the same
working_dir, or an obviously identical title/topic, into one study (e.g. amy-studyfolder and aDesktop-my-studyvariant). State the rationale when bundling; if unsure, do not bundle. - Concrete next actions. No meaningless actions like "keep going." Review each card's
next_actions; if vague, find a more concrete phrasing inprogress_summary. - Sorting. Sort the overview table by status (active → idle → stalled → done), then by last activity descending.
- Show empty log directories too. List zero-session directories as "no logs" at the bottom of the table — they may be projects the user created but never started.
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.
- 2mo ago First seen · 51 lines · 41 tokens per session scan A 9b166e1abada
dashboard-curator is an agent published in the GitHub repository jmleetpl/claude-research-dashboard (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 728 once invoked, about $0.0002 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 2026-08-31.
dashboard-curator compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dashboard-curatorjmleetpl/claude-research-dashboard | Agent | 2 | 4mo ago | MIT | A | 41 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |