MichaelYcJo

29 mods across 1 repository, 1 stars between them.

specseal

01

MichaelYcJo/SpecSeal

Plugin Claude Code

SpecSeal — specs, sealed: implement/review agent chain, evidence ledger with drift detection, hook-enforced gates.

1 yesterday A tokens not measured original MIT

specseal

02

MichaelYcJo/SpecSeal

Plugin Claude Code

SpecSeal — specs, sealed: an implement/review agent chain with hook enforcement, an evidence ledger with drift detection, and a tool-agnostic review handoff protocol.

1 yesterday A tokens not measured original MIT

SpecSeal CLAUDE.md

03

MichaelYcJo/SpecSeal

Instructions file

Claude Code instructions for MichaelYcJo/SpecSeal, covering tooling, safety, session cost, git and repo rule — no real identifiers in examples or fixtures.

1 yesterday A 1,159 tokens original MIT

scribe

04

MichaelYcJo/SpecSeal

Agent

Migration fact-finder. Spawn only in projects with a migration config (.specseal/parity.md) to establish what the original code actually does — facts with coordinates, no verdicts. Called by smith during implementation and by the review orchestrator during parity review.

1 yesterday A 57 tokens original MIT

smith

05

MichaelYcJo/SpecSeal

Agent

Implementation agent. Spawn for feature work, ticket implementation, refactors, and incorporating review feedback. Follows the implement skill (SDD procedure, three-axis document layout); hands finished work to the review chain.

1 yesterday A 44 tokens original MIT

warden

06

MichaelYcJo/SpecSeal

Agent

Review agent. Spawn to review a PR, diff, or branch — spec compliance first, then quality. Reads earlier review rounds and inherits their verdicts; returns a report for the orchestrator to verify and post.

1 yesterday A 46 tokens original MIT

PreToolUse

07

MichaelYcJo/SpecSeal

Hook

Runs before the agent uses a tool for Bash, Agent, Task and Skill tool calls, executing dispatch.py via python3 (3 commands). From MichaelYcJo/SpecSeal.

1 yesterday A tokens not measured original MIT

PostToolUse

08

MichaelYcJo/SpecSeal

Hook

Runs after a tool call finishes for Bash, Write, Edit and NotebookEdit tool calls, executing dispatch.py via python3 (2 commands). From MichaelYcJo/SpecSeal.

1 yesterday A tokens not measured original MIT

SessionStart

09

MichaelYcJo/SpecSeal

Hook

Runs when a session starts, executing dispatch.py via python3. From MichaelYcJo/SpecSeal.

1 yesterday A tokens not measured original MIT

audit

10

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Validate project-specific rules a linter cannot express, declared as .claude/audit-rules/.md. Use when: checking conventions this repo wrote down for itself before a commit or release. NOT for: formatting or style a linter already enforces, security review (security-audit), or comparing a spec against the code…

1 yesterday A 77 tokens original MIT

build-fix

11

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Resolve build, compile, and type-check errors at their cause instead of suppressing them. Use when: the build does not produce output — type errors, missing modules, syntax or config failures. NOT for: code that compiles but behaves wrong (that is debug).

1 yesterday A 62 tokens original MIT

checkpoint

12

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Establish a rollback point before an operation that is hard to undo, and get explicit approval with the blast radius stated. Use when: deleting files, migrating schemas, renaming across the codebase, or changing a core abstraction — where reverting later is not just a git command. NOT for: ordinary refactors that a…

1 yesterday A 73 tokens original MIT

code-review

13

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Two-stage review methodology (spec compliance, then quality) with comparison axes, cross-session review records, and re-review inheritance. Use when: reviewing a PR or diff, re-reviewing after fixes, orchestrating reviewer agents. NOT for: implementing fixes (use implement), style-only linting a formatter can do, or a…

1 yesterday A 113 tokens original MIT

confidence-check

14

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Readiness check before implementing: does something equivalent already exist, is the API verified against the installed version, is the cause of the bug actually understood rather than guessed. Reports which checks are unsatisfied — no score, since any single miss is the whole answer. Use when: about to build…

1 yesterday A 127 tokens original MIT

debug

15

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Find the cause of wrong behavior: reproduce, locate, one hypothesis at a time, then a failing test before the fix. Use when: the code runs but produces the wrong result, or a test fails. NOT for: build, compile, or type-check errors — nothing runs there, so there is nothing to reproduce (that is build-fix).

1 yesterday A 77 tokens original MIT

evidence-check

16

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Verify that the evidence ledger's spec-to-code coordinates still resolve — broken links fail, ranges touched since the baseline demand re-verification. Use when: checking ledger health, before merging spec-driven work, wiring the check into CI, or after large refactors. NOT for: judging whether the code is CORRECT …

1 yesterday A 87 tokens original MIT

evidence-ci

17

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Wire the ledger drift check into this repo's CI — vendor the checker and write the workflow, so drift fails a build instead of waiting to be run by hand.

1 yesterday A 37 tokens original MIT

feature-planner

18

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Decompose work into ordered tasks with dependencies mapped, then lock scope in writing before starting. Use when: the work spans more than about three files or needs phasing, and no plan exists yet. NOT for: firing on your own while the smith is driving — its design gate invokes this when decomposition is what the…

1 yesterday A 81 tokens original MIT

gap-analysis

19

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Compare a design or spec document against what was actually built — API surface, data model, business logic — and list what is missing, extra, or divergent. Use when: a written design exists and someone needs to know how far the implementation has drifted from it. NOT for: checking that ledger coordinates still…

1 yesterday A 101 tokens original MIT

implement

20

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Spec-driven implementation methodology: document layout (specs/ + .specseal/), policy-first judgment, evidence feedback, and review incorporation. Use when: implementing a feature, starting a ticket — including deciding how to start one, incorporating review feedback, or when a repo needs its document layout…

1 yesterday A 131 tokens original MIT

learn

21

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Record an insight that cost real debugging effort and cannot be recovered from a search — project-specific causes, dependency quirks, the reason behind an architectural choice. Use when: something was just figured out the hard way and the next session would otherwise pay for it again. NOT for: narrating ordinary work…

1 yesterday A 85 tokens original MIT

legacy-parity

22

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Behavior-equivalence methodology for legacy migrations: three-way judgment (policy ↔ original code ↔ new code) with original-preservation as the default. Use when: a project declares a migration config (.specseal/parity.md), porting or reviewing ported behavior, judging divergence from a legacy original. NOT for…

1 yesterday A 81 tokens original MIT

parity-setup

23

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Declare that this repo ports behavior from another codebase — find the original, record the baseline, write .specseal/parity.md.

1 yesterday A 32 tokens original MIT

preset-setup

24

MichaelYcJo/SpecSeal

Skill Claude CodeCodex

Merge the specseal CLAUDE.md block into the user's CLAUDE.md with semantic dedup — propose, get approval, then apply.

1 yesterday A 33 tokens original MIT