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 skills add alexmond/alexmskills --skill prompt-coachgit 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/skills/alexmond/alexmskills/prompt-coach)<a href="https://agentmods.dev/skills/alexmond/alexmskills/prompt-coach"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/prompt-coach/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/alexmond/alexmskills/prompt-coach"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/prompt-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 79 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 90 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 115 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 161 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 202 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00177 | $0.08541 |
| Opus 5 | $0.00088 | $0.04270 |
| Sonnet 5 | $0.00035 | $0.01708 |
| Haiku 4.5 | $0.00018 | $0.00854 |
Grade A, and why
prompt-coach 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 — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-coach
Quick start
60-second setup
/plugin marketplace add alexmond/alexmskills
/plugin install prompt-coach@alexmskills
/reload-plugins
Restart the session so the UserPromptSubmit hook registers. Then just prompt Claude normally — the coach analyzes every prompt in the background and nudges when a rule matches.
What you'll see when a rule fires
As of v0.34 the coach is a collaborator (not a nagger): when a rule fires, Claude reads your prompt in context and rewrites it with the fix baked in, at the top of its response:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💬 prompt-coach — I read your prompt as:
"in src/auth/login.js, update handleLogin() to reject empty
password submissions with a 422 and a 'password required'
message. Keep the existing test suite green."
Changes:
[1] Named the file + function (was: 'the login flow')
[2] Made the behavior explicit + added a guardrail
Sources: https://…/be-clear-and-direct
Proceeding with this rewrite now — reply "no" to redo from your original, or "edit" to adjust.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ Working from the rewrite.
<Claude answers your question from here, using that prompt.>
On a clean prompt you instead get a one-line ✓ heartbeat (v0.35). The coach is a suggestion, not a block — Claude answers your prompt normally. By default (v0.43) it proceeds honestly: the block says it's proceeding (not "reply yes to proceed") and Claude opens with a ▸ Working from the rewrite / your original line so you always see which prompt drove the answer; silence = accept, and a no/edit next turn corrects. Prefer a real pause? Set collaborator_gate: true and Claude stops after the block and waits for your yes/no/edit (one extra round-trip per fired prompt). Rules graduate to "mastered" once you've demonstrated the good technique min_demonstrations times (default 3, v0.40 earned-mastery model), then the next dormant rule activates.
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 · 577 lines · 177 tokens per session scan A 7538c7c99a9e
prompt-coach is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 3d ago), licensed MIT. It adds 177 tokens to every session and 8,541 once invoked, about $0.0009 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
nativeprompt
A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
ag-referencia-prompt-guide
Guia canonico de prompts para gerar UI em Claude/Cursor/Lovable/v0. Estrutura 6 blocos (Contexto/Layout/Estilo/Refs/Constraints/Entregavel). Invocar ANTES de pedir geracao de UI.
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
c-ai
Query LLMs from the CLI — pipe text for summarization, chat interactively, use local or cloud models with llm or aichat.
prompt-engineering
Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…