roymondliao

31 mods across 1 repository, 2 stars between them.

samsara

02

roymondliao/samsara

Plugin Claude Code

向死而驗 — Death-first development workflow. Existential accountability for every line of code.

2 6d ago A tokens not measured

samsara AGENTS.md

03

roymondliao/samsara

Instructions file CodexOpenCode

AGENTS.md instructions for roymondliao/samsara, covering project conversation guidelines, python, infrastructure and when a command fails or produces unexpected output.

2 6d ago A 313 tokens

samsara CLAUDE.md

04

roymondliao/samsara

Instructions file

Claude Code instructions for roymondliao/samsara: MUST read and STRICTLY follow AGENTS.md — these are mandatory execution conventions, not suggestions.

2 6d ago A 22 tokens

auto-gatekeeper

05

roymondliao/samsara

Agent

Staff-level workflow decision authority for Samsara auto mode — answers human-equivalent gate questions and is the sole writer of validated append-only decisions.

2 6d ago A 33 tokens

roymondliao/samsara

Agent

Structural code quality review agent — assesses structural truth-telling against 9 yin principles (S/O/L/I/D + Cohesion/Coupling/DRY/Pattern). Produces PASS/PASSWITHCONCERNS/FAIL/UNKNOWN verdicts with mandatory file:line evidence on any non-UNKNOWN output.

2 6d ago A 67 tokens

code-reviewer

07

roymondliao/samsara

Agent

Yin-side code review agent — asks deletion before correctness, identifies dishonest naming and silent rot paths. Determines execution model and loads domain-specific reference files. Returns UNKNOWN for unrecognized or unsupported domains.

2 6d ago A 43 tokens

implementer

08

roymondliao/samsara

Agent

Death-test-first implementer — writes death tests before unit tests, produces scar reports, enforces STEP 0 prerequisite questions.

2 6d ago A 27 tokens

yin-explorer

11

roymondliao/samsara

Agent

Analyzes committed code for silent failure, hidden coupling, assumptions, and death impact after structural evidence exists.

2 6d ago A 24 tokens

SessionStart

12

roymondliao/samsara

Hook

Runs when a session starts on startup, clear and compact, running an inline shell check (2 commands). From roymondliao/samsara.

2 6d ago A tokens not measured

codebase-map

13

roymondliao/samsara

Skill Claude CodeCodex

Use when entering a Git project for the first time or when its committed HEAD no longer matches the recorded codebase map.

2 6d ago A 27 tokens

debugging

14

roymondliao/samsara

Skill Claude CodeCodex

Use when existing deployed or runtime behavior produces an observed failure, alert, or user-reported regression.

2 6d ago A 22 tokens

fast-track

15

roymondliao/samsara

Skill Claude CodeCodex

Use when state-changing work has a proven bounded damage radius, no unresolved design question, and deterministic verification.

2 6d ago A 23 tokens

implement

16

roymondliao/samsara

Skill Claude CodeCodex

Use when a plan with tasks exists and you need to execute implementation — requires index.yaml and tasks/ directory.

2 6d ago A 23 tokens

iteration

17

roymondliao/samsara

Skill Claude CodeCodex

Use when implementation is committed and task scar reports may contain unresolved, accepted, deferred, blocked, or cross-task wounds before shipping.

2 6d ago A 27 tokens

level-analysis

18

roymondliao/samsara

Skill Claude CodeCodex

Use when a decision-maker needs comparable engineering options, broader scope, or an independent view before making a difficult technical judgment.

2 6d ago A 26 tokens

planning

19

roymondliao/samsara

Skill Claude CodeCodex

Use when approved pre-thinking output must become an implementation task graph and acceptance contract without reopening design decisions.

2 6d ago A 21 tokens

pre-thinking

20

roymondliao/samsara

Skill Claude CodeCodex

Use when research output is complete and planning would otherwise need to assume design, task-shape, structural boundaries, or evaluation details before implementation planning.

2 6d ago A 31 tokens

research

21

roymondliao/samsara

Skill Claude CodeCodex

Use when starting new feature work, investigating a problem, or when the user describes something they want to build — before any planning or implementation.

2 6d ago A 29 tokens

samsara-bootstrap

22

roymondliao/samsara

Skill Claude CodeCodex

Injected at session start — establishes samsara axiom, agent constraints, and skill discovery for the session.

2 6d ago A 25 tokens

validate-and-ship

23

roymondliao/samsara

Skill Claude CodeCodex

Use when Iteration has committed a ready-for-validation checkpoint and one candidate must be validated, documented, and prepared for delivery.

2 6d ago A 29 tokens