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 mehrad-dm/mastermind --skill interviewgit 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/interview)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/interview"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/interview/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/mehrad-dm/mastermind/interview"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 54 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.
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 | $0.00143 | $0.02767 |
| Opus 5.5 | $0.00057 | $0.01107 |
| Sonnet 5.5 | $0.00029 | $0.00553 |
| Haiku 4.5 | $0.00014 | $0.00277 |
Grade A, and why
interview 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 15d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Interview
A precise spec is cheaper than a wrong build. Time spent making the spec exact pays off more than time
watching the implementation (~/.mastermind/engineering/core/product-sense.md, ~/.mastermind/engineering/core/agent-loop.md). This produces the what,
not the code.
Their own words stay theirs: propose, never rewrite unasked (~/.mastermind/engineering/core/rigor.md → Stay in scope).
First, say what you think they're asking for
Lead with your reading of the ask and how sure you are: a wrong guess gets corrected faster than a blank question gets answered. One or two lines, then proceed or ask:
Reading it as: a way to see which jobs failed overnight, so the morning starts with a fix not a search.
~70% sure: what I'm missing is whether "failed" includes timeouts.
If you do have to ask: one question at a time, and answer it yourself first. A batch of questions hands your job back and makes the user do technical work; asking blind makes them generate an answer from nothing. Ask the single question that unblocks the next decision, with your recommendation attached, people correct a wrong guess far faster than they compose an answer:
Q: Should a failed import roll back the whole batch, or keep the rows that parsed?
I'd keep the good rows and report the failures: a 5,000-row file failing on row 4,900
is the case people actually hit. Say the word if you'd rather it be all-or-nothing.
Look facts up rather than asking for them: the stack, the conventions, what the code already does are yours to find. Only the decisions are theirs.
Two things to catch, because both hide a wrong build behind an apparent agreement:
- The out-of-scope half. Most misalignment is silent disagreement about what is not being built, which is why step 2 below names it explicitly rather than leaving it implied.
- A hollow yes. "Whatever you think," "sounds good," and silence are not confirmations; they're delegation, politeness, and fatigue. Restate the ask concretely and get a real one, or decide it yourself and say plainly that you did.
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.
- 15d ago Changed · +37 lines · +143 tokens per session aa49ef3811a1
- 1mo ago First seen · 148 lines · 0 tokens per session scan A da0cb766a887
interview is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 143 tokens to every session and 2,767 once invoked, about $0.0006 per session on Opus 5.5. 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
st-full-workflow
Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…
code-sec-review
Static security review that hunts exploitable vulnerabilities, prioritizing unauthenticated and cross-tenant attack paths.
agent-decision
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
code-quality-review
Reviews code and plans against the project's coding rules.
review-loop
Two-mode review loop — single reviewer per epic, three reviewers for full branch.
setup-new-acpx-key
Configure the API key (or other credential) for a registered ACPX agentid (claude/codex/cursor/gemini/qwen/copilot/pi/droid/iflow/kilocode/kimi/kiro/opencode/tlamatini) end-to-end across data.keys, config.json (top-level + acpx.agents. .env), regensecrets.py, and verification via acpdoctor.