tmusser

32 mods across 3 repositories, 10 stars between them.

analyze-mini

01

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support a safe build decision.

not rated 5 +1 7d ago A 27 tokens original MIT

build-one

03

tmusser/ai-engineering-skills

Skill Claude CodeCodex needs its repo

Implement exactly one planned slice after scope is frozen, without exceeding the spec ceiling or carrying known analysis debt into the build.

not rated 5 +1 changed 8d ago A 27 tokens original MIT

ceremony-budget

04

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Choose the smallest workflow that still buys back enough attention and safety for the task.

not rated 5 +1 changed 10d ago A 20 tokens original MIT

constitution-lite

06

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Define a tiny set of stable, non-negotiable agent authority boundaries for repeated or delegated work without duplicating CLAUDE.md, AGENTS.md, or task specs.

not rated 5 +1 7d ago C 38 tokens original MIT

context-check

07

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.

not rated 5 +1 7d ago A 34 tokens original MIT

diagnose-loop

08

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Diagnose reproducible failures with hypothesis-driven fixes and bounded retries.

not rated 5 +1 changed 1mo ago A 17 tokens original MIT

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, using optional read-only research fan-out while separating evidence, tensions, decisions, assumptions, and blockers before contract language is written.

not rated 5 +1 changed 10d ago A 57 tokens original MIT

handoff

10

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Compress project context into HANDOFF.md with workflow state, analysis checkpoint, next gate, verification, current hypothesis, freshness anchors, optional gotcha references, and a resume packet for the next agent session.

not rated 5 +1 changed 9d ago A 43 tokens original MIT

lean-mode

11

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.

not rated 5 +1 changed 10d ago A 29 tokens original MIT

mini-spec

12

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Create a compact, reference-first SPEC.md that defines the task-specific delta, non-goals, likely failure modes, spec ceiling, and verification target without paraphrasing richer authoritative sources.

not rated 5 +1 changed 8d ago A 40 tokens original MIT

scope-freeze

13

tmusser/ai-engineering-skills

Skill Claude CodeCodex needs its repo

Explicitly limit blast radius before any implementation or file changes.

not rated 5 +1 changed 8d ago A 16 tokens original MIT

ship-mini

14

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Run a lightweight activation GO or NO-GO gate only when verified work is about to gain material real-world side effects, autonomy, permissions, or production/shared-state impact.

not rated 5 +1 changed 10d ago A 37 tokens original MIT

teach-back

15

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Transfer ownership of a verified implementation by testing and repairing the human's understanding of its behavior, decisions, and failure modes without turning every task into a tutorial.

not rated 5 +1 7d ago A 34 tokens original MIT

test-mini

16

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Add focused deterministic tests, fixtures, or smoke checks.

not rated 5 +1 7d ago A 14 tokens original MIT

thin-plan

17

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Convert a mini-spec into 3-7 vertical implementation slices.

not rated 5 +1 7d ago A 16 tokens original MIT

tool-noise-guard

18

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Passive guardrail that compacts repetitive tool-result envelopes, preserves decision-relevant anchors and deltas, and suppresses redundant re-fetches without pretending prior context disappeared.

not rated 5 +1 7d ago A 39 tokens original MIT

verify-contract

19

tmusser/ai-engineering-skills

Skill Claude CodeCodex needs its repo

Record clear evidence that a task works, including commands, results, remaining risks, scope adherence, and whether the implementation stayed under the spec ceiling.

not rated 5 +1 changed 8d ago A 32 tokens original MIT

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Reactivate the smallest set of decision-governing constraints immediately before a consequential action, without introspection, full-context summarization, or a new durable artifact.

not rated 5 +1 7d ago A 36 tokens original MIT

operator-profile

21

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Create a compact operator preference profile that tunes safe workflow defaults without overriding task contracts, repository instructions, safety boundaries, or required verification.

not rated 5 +1 7d ago A 29 tokens original MIT

eco-mode

22

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Keep a small, budgeted working context for low-cost model execution without weakening task contracts, required sources, or verification.

not rated 5 +1 7d ago A 27 tokens original MIT

brief-me

23

tmusser/context-to-action-skills

Skill Claude CodeCodex

Catch the user up from messy workplace context and surface what needs attention.

not rated 3 changed 29d ago A 17 tokens original MIT

clear-ask

24

tmusser/context-to-action-skills

Skill Claude CodeCodex

Turn vague workplace context into a crisp ask with clear ownership and timing.

not rated 3 1mo ago A 18 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: