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 skills/mehrad-dm/mastermind/learnnpx skills add mehrad-dm/mastermind --skill learngit clone --depth 1 https://github.com/mehrad-dm/mastermindWrote 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/mehrad-dm/mastermind/learn)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/learn"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/learn.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 | $0.00065 | $0.00653 |
| Opus 5 | $0.00032 | $0.00327 |
| Sonnet 5 | $0.00013 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
learn 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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Learn
The invokable form of ~/.mastermind/engineering/core/agent-loop.md → "Learn the stack before you build." Topic/task:
$ARGUMENTS. Goal: reach genuine, current understanding: enough to build to standard: fast, and
cheap on context.
1. Detect what's actually used
Read package.json/lockfile, configs, and representative source to see the exact stack (framework +
versions, styling, state, data, test runner) and the team's conventions. Installed versions matter,
APIs drift, so learn the version that's actually here.
2. Map the skill-tree
Use the relevant role/topic map on the website roadmap.sh as the checklist of what matters and to spot your gaps. Learn just the branch the task touches; the rest of the tree waits.
3. Learn to current standards
Read the primary docs for the specific APIs the task needs (verify against the installed version)
and skim one battle-tested example (the field's curriculum.md lists them). Prefer primary sources;
read them fresh, since memory goes stale (the field's learning-sources.md).
4. Ground it in this codebase
Grep for how the pattern is already used here and match it. Consistency beats novelty.
5. Challenge your assumptions before you build
The costly bugs come from unchecked assumptions. Before committing code:
- List what you believe about the APIs you'll use (behavior, signatures, return values, limits,
versions, edge cases), specifically ("
getFilestreams any size", true?). - Answer from the source yourself first: verify each against the docs/types/actual source (for the installed version). Confirm ✓, correct ✗, or mark unknown ❓. Anything the code/docs answer, you answer.
- For each remaining unknown, propose a resolution: a bare flag is half the job. State a best guess
+ confidence ("probably streams; ~70%") so a human can confirm or correct, not author it. Serve
interdependent unknowns one at a time. Anything still unconfirmed becomes an explicit risk or a tiny
prototype, never a silent guess. No load-bearing assumption ships unverified.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 47 lines · 0 tokens per session scan A 45adb2192fa8
learn is a skill published in the GitHub repository mehrad-dm/mastermind (24 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 653 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gstack-roles
Role-based AI specialist system. Defines 23 specialist roles and teaches the AI to adopt the correct role before each task phase, like a virtual engineering team.
competitive-programming-expert
Use this skill when user needs to solve competitive programming problems. Applicable to LeetCode, Codeforces, AtCoder and similar platforms. Triggers include: algorithm problem, coding challenge, time complexity analysis, data structure implementation, TLE (Time Limit Exceeded), MLE (Memory Limit Exceeded).
learning-memory
Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.
your-skill-name
State the educational problem this skill solves and the intended outcome.
challenge-generator
Use when generating personalized practice challenges calibrated to the learner's weak areas, level, and project context.
interview-mode
Use when simulating a technical interview to build confidence, expose reasoning gaps, and train structured communication under pressure.