Install
$ agentstack add skill-mehrad-dm-mastermind-mastermind-debug ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
MasterMind — Debug
Hard bugs are lost by guessing and patching symptoms. This is the disciplined loop that finds the actual cause. Bug: $ARGUMENTS. Grounded in ~/.mastermind/engineering/core/rigor.md and ~/.mastermind/engineering/core/agent-loop.md.
The cardinal rule: understand the mechanism before you change a line. A fix you can't explain is a coincidence, not a fix.
The six phases
- Reproduce deterministically. Find the smallest reliable trigger and a check that goes red on the
bug (a failing test, a script, a repro URL/steps). No repro → no fix; keep narrowing inputs until it fails on demand. This red check is also your definition of "fixed."
- Localize. Bisect the space — git bisect across commits, binary-search the code path, add
instrumentation/logs at boundaries. Read the actual code and the actual data/state at the failure point; don't theorize from memory. Narrow to the smallest region that still reproduces.
- Hypothesize. List the credible causes (usually 2–4), ranked. State, for the top one, the exact
mechanism: "X happens because Y is Z at line N." Reason from first principles and the runtime model, not from superstition.
- Test the hypothesis. Prove or kill it with a targeted experiment — inspect the value, toggle the
condition, add an assertion. Confirm the mechanism before fixing. If the experiment refutes it, go back to (3) with what you learned. Don't shotgun-change multiple things.
- Fix the root cause, not the symptom (
~/.mastermind/engineering/core/rigor.md). Address why the bad state was possible —
ideally make it unrepresentable (types, invariants, a reshaped data structure so the edge case disappears — ~/.mastermind/engineering/core/mindset.md). Never suppress an error to green the check.
- Verify + guard. Confirm the red check now passes and nothing else broke (typecheck/lint/tests/
build). Add a regression test that would have caught this — the bug must not be able to return silently. Show the evidence.
After
Run mastermind-levelup (capture) to record the class of bug and its lesson in the active field's lessons.md, so MasterMind doesn't relearn it. Report: root cause, the fix, and the guard added.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mehrad-dm
- Source: mehrad-dm/mastermind
- License: MIT
- Homepage: https://mastermind.mehrad.me
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.