drubinstein/terry

A collection of Claude Code skills for general software-engineering work — bug reproduction (jamie), root-cause debugging (sherlock), performance (brendan), empirical iteration (andrej), and agent-fleet orchestration (terry).

1Stars on the repository
7Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

andrej

01

drubinstein/terry

Skill Claude CodeCodex

Invoke when iterating toward a fix/optimization/answer against a live system and tempted to guess from sparse signals — an observe→analyze→act loop over instrumentation + a scalar metric + one-variable bounded experiments + a keep-or-revert gate + an append-only ledger; covers instrument-before-you-hypothesize, the…

1 2mo ago C 102 tokens original MIT

brendan

02

drubinstein/terry

Skill Claude CodeCodex

Invoke when a system is slow, saturated, regressed, or near capacity and you are tempted to guess the bottleneck or reach for a random tool — Brendan Gregg's systems-performance methodology. Covers the USE method (check utilization, saturation, errors for EVERY resource), the 60-second triage checklist, TSA /…

1 2mo ago A 163 tokens original MIT

jamie

03

drubinstein/terry

Skill Claude CodeCodex

Invoke when you have a bug report or issue and need to confirm it's REAL before anyone fixes it — turn the report into a precise claim, faithfully recreate the reporter's conditions (the version they hit, config, data, platform, timing), build a minimal reliable reproduction, quantify how often it fires, and return a…

1 2mo ago A 131 tokens original MIT

ronald

04

drubinstein/terry

Skill Claude CodeCodex

Invoke when comparing models or prompts and you want evidence, not a vibe check — choosing a model for a task (opus vs sonnet vs haiku; Claude vs Codex vs Gemini), A/B testing prompt variants, running a model/prompt bake-off or eval, or confirming a prompt change actually helped rather than got lucky. Runs a…

1 2mo ago A 140 tokens original MIT

sherlock

05

drubinstein/terry

Skill Claude CodeCodex

Invoke when a bug resists the obvious explanation and you're stuck — a "this is impossible / can't be happening" heisenbug, an intermittent or nondeterministic failure with many candidate causes, a regression with many possible culprits, a works-here-fails-there environment bug, or the moment you think "I've checked…

1 2mo ago A 146 tokens original MIT

terry

06

drubinstein/terry

Skill Claude CodeCodex

Invoke when orchestrating a FLEET of parallel long-running agent tasks via a priority-queue manager over git worktrees, OR when you want a producer-consumer task queue for agents that caps concurrency to avoid OOM and pace token spend on a budget — agent queue + task list + dispatched agents + a self-pacing heartbeat…

1 2mo ago A 106 tokens original MIT