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 commands/alexmond/alexmskills/dashboardgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/dashboard)<a href="https://agentmods.dev/commands/alexmond/alexmskills/dashboard"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/dashboard.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 | $0.00017 | $0.00750 |
| Opus 5 | $0.00009 | $0.00375 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-coach:dashboard
Start the coach's lightweight local web dashboard — a zero-dependency
(Python stdlib only) server bound to 127.0.0.1 that shows stats, mastery by
tier with reference-URL links, and a live config editor (writes go through
the same schema validation the CLI uses).
What to do
-
Locate the plugin's
scripts/serve.py(installed cache path~/.claude/plugins/cache/alexmskills/prompt-coach/*/scripts/serve.py, else the dev checkout). -
Launch it in the background so this session stays interactive, pointed at the current repo (for repo-scoped config):
python3 <plugin>/scripts/serve.py --cwd "$PWD" --port 8765If port 8765 is taken, pass
--port 0to get a free one; read the printedhttp://127.0.0.1:<port>/line and give the user that URL. -
Print the URL and tell the user to open it. Note that it's local only (127.0.0.1) and edits the same
~/.claude/prompt-coach/+ repo.claude/prompt-coach/state the hook and CLI use. -
To stop it later: kill the background process (or Ctrl-C if foreground).
What the dashboard shows
- Stats — prompts analyzed, mastered / inactive / in-progress / dormant counts.
- Mastery — every rule grouped by tier (L1–L6) with a status badge,
demos/minprogress,fires, its guidance, and clickable reference URLs (Anthropic guide + every cited source). A per-rule reset button. - Config — every schema key with its description, current value + scope, and
a type-aware control (checkbox / number / select / text). Editing saves
live to the chosen scope (global or repo, selectable top-right).
↺resets a key to default. - Options — reset-all-mastery, refresh, open the Anthropic guide.
- Library — browse Anthropic's Claude Code Prompt Library templates by phase / category / role, with a text filter (v0.47).
- Sources — every citation in the catalog, deduped and ranked by importance (official Claude Code / Anthropic docs → foundational canon → practitioner), each linking out and listing the rules that cite it (v0.48).
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.
- 6d ago First seen · 66 lines · 17 tokens per session scan A 10a1554be914
dashboard is a command published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 750 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.