Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install pm-job-searchWrote 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/archugunov/pm-job-search/dashboard)<a href="https://agentmods.dev/skills/archugunov/pm-job-search/dashboard"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/dashboard/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/archugunov/pm-job-search/dashboard"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/dashboard.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 | $0.00144 | $0.01419 |
| Opus 5 | $0.00072 | $0.00709 |
| Sonnet 5 | $0.00029 | $0.00284 |
| Haiku 4.5 | $0.00014 | $0.00142 |
Grade A, and why
dashboard 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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dashboard
Launches the pm-job-search visual dashboard.
What it does
- Starts a local Python server (
plugin/dashboard/serve.py) on port 7890 (or the next free port up to 7900). - Opens the user's default browser to
http://localhost:<port>. - Prints the URL to chat so the user can copy it if auto-open fails.
- Waits in the foreground until the user hits ctrl-C.
The dashboard provides:
- A top status bar showing pipeline counts, weekly progress vs
strategy.mdtargets, and days-to-target-offer countdown. - A grouped applications table (toggle Status / Tier) with inline status dropdowns; click any row to open the notes drawer.
- A bottom panel rendering the latest
daily-brief-*.md(with a stale-brief banner when older than today). - To add a new position: run
/pm-job-search:evaluate-position <link>in Claude Code. The dashboard does not write new positions itself.
When to invoke
- User types
/dashboard. - User asks to "open the dashboard", "show me my pipeline", "launch the visual view".
- User wants to do bulk pipeline maintenance (status sweeps, quick notes against several companies).
How to invoke
The skill runs one shell command:
python3 "${CLAUDE_PLUGIN_ROOT}/dashboard/serve.py" --userdata "$(pwd)/userdata"
${CLAUDE_PLUGIN_ROOT} resolves to the plugin install directory. $(pwd) resolves to the user's workspace root (the dir containing userdata/).
If the user is running this from somewhere other than their workspace root, ask for the workspace path and pass it explicitly: --userdata <path>/userdata.
Failure modes and what to do
- Bundle missing (
error: dashboard bundle not found). The plugin'sdist/is not committed or got deleted. Tell the user to reinstall the plugin; this should not happen in a clean install. - Port range exhausted (
error: no free port in 7890-7899). Something else is using all ten ports. Suggest--port 7900(or higher) explicitly. - userdata not found. The user is in the wrong directory. Ask for the workspace path.
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.
- 11d ago First seen · 99 lines · 144 tokens per session scan A 6778dacb752d
dashboard is a skill published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 16d ago), licensed MIT. It adds 144 tokens to every session and 1,419 once invoked, about $0.0007 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
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
alive-create
Scaffold a new walnut -- venture, experiment, person, life area, project.
alive-project
Regenerate now.json projections for all walnuts (mechanical, no approval needed).
pilot
One autonomous Pilot cycle - fetch the agenda, execute the top item, journal, exit. Injected by the terminal host - not for manual invocation loops.