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/masterygit 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/mastery)<a href="https://agentmods.dev/commands/alexmond/alexmskills/mastery"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/mastery.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 | $0.00048 | $0.00762 |
| Opus 5 | $0.00024 | $0.00381 |
| Sonnet 5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
mastery 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 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.
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:mastery
Direct top-level access to the mastery view. Same output as /prompt-coach:config mastery but you don't have to type the config prefix.
What to do
-
Locate the config script (same helper the other commands use):
ls ~/.claude/plugins/cache/alexmskills/prompt-coach/*/scripts/config.py 2>/dev/null | tail -1Fallback for dev checkout:
~/IdeaProjects/alexmskills/plugins/prompt-coach/scripts/config.py -
Parse the user's input:
User says Run (no arg) python3 <path> mastery"as JSON" / "json" python3 <path> --json mastery"reset " python3 <path> mastery-reset <rule-id>(dry-run first, then ask to confirm)"reset all" / "reset everything" python3 <path> --dry-run mastery-reset-all, show preview, ask to confirm -
Render the script's stdout verbatim. The output already has the analysis section built in (v0.26+): mastery evidence quality (well-tested vs barely-tested vs untested), untested masteries listed with a suggestion, and close-to-mastery rules surfaced.
-
Calibrated follow-up (≤2 sentences):
- Many untested masteries (≥5) → note that this often means the rules don't apply to how you prompt, not that you've internalized them. Suggest picking one to reset if the user wants active coverage.
- Rules close to mastery → mention them; a couple more clean prompts and they graduate.
- Zero mastered rules → first-time user; explain that mastery is
earned by demonstration: a rule masters once you actually use its good
technique (its positive detector fires)
min_demonstrationstimes (default 3) with no recent relapse — clean streaks alone no longer master a rule.
Natural-language routing
| Prompt | Route |
|---|---|
| "show mastery" / "my mastery" / "how am I doing" | mastery |
| "check my mastery" / "analyze mastery" | mastery |
| "which rules mastered" | mastery (analysis section covers it) |
| "reset " | mastery-reset <rule-id> |
| "reset all my mastery" | mastery-reset-all |
| "is any of my mastery suspicious" | mastery (analysis section flags untested) |
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 · 66 lines · 48 tokens per session scan A 44f4291e9b54
mastery is a command published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 762 once invoked, about $0.0002 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.