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 alexmond/alexmskills/plugin install prompt-coachWrote 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/analyze)<a href="https://agentmods.dev/commands/alexmond/alexmskills/analyze"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/analyze.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 | $0.00019 | $0.00747 |
| Opus 5 | $0.00010 | $0.00374 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade B, and why
analyze scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
clickable). Keep the voice of the collaborator block: propose, don't preach. How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-coach:analyze
On-demand prompt analysis. Unlike the passive hook — which only checks the handful of active rules and stays quiet — this runs the full 42-rule catalog + positive detectors against either a prompt you name or your recent prompt history, then coaches concrete improvements using the skill's prompting knowledge.
What to do
-
Locate the config script (same resolution as
/prompt-coach:config):${CLAUDE_PLUGIN_ROOT}/scripts/config.py, else the dev checkout path. -
Route on the argument:
User intent Run analyze a prompt they pasted / "analyze this: " --json analyze "<text>""analyze my last N prompts" / "review my last N" / "how have I been prompting" --json analyze --last N(default N=10)analyze the prompt before this command (their previous turn) read it from the transcript, pass as analyze "<text>"Always pass
--json(before the verb) and--cwd <repo>so you get structured data. -
Single prompt → the JSON gives
fired[](each with id, tier, name, guidance, url) andpositives[]. Produce a short coaching report:- If
clean: true, say so and name any positive habits detected. - Otherwise, for each fired rule give a one-line "why it fired + the fix", then offer a rewritten prompt that resolves the top 2–3 issues. Cite the rule URLs (they're clickable). Keep the voice of the collaborator block: propose, don't preach.
- If
-
History (
--last N) → the JSON gives per-promptfired[], arule_frequencymap, andrule_detail. Produce a pattern report:- Lead with the clean rate (e.g. "6/10 fired no rule").
- Name the top 2–3 recurring rules and what they mean, with their doc URLs.
- Give ONE concrete habit to focus on next (the highest-frequency fundamental).
- Optionally show the single worst prompt with a rewrite as a worked example.
-
Render the script's own output only if the user asked for raw data; otherwise fold it into your coaching narrative.
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.
- 5d ago First seen · 59 lines · 19 tokens per session scan B 4bc490384ec1
analyze is a command published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 747 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.