zookanalytics/gc-toolkit

A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

This repository also configures its own agents. See what gc-toolkit tells them →

5Stars on the repository
26Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

demo:capture

01

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Records a narrated, captioned MP4 demo of a rig's app with the SprintShow engine — a demo-script drives the browser, each step is proof-checked against the live DOM, and ffmpeg assembles the clip.

not rated 5 changed 5d ago A SkillSpector: warn 49 tokens original MIT

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when you are about to write or file a durable document — an analysis, decision record, research synthesis, spec, or design note. Fires before you create the file so it lands in the right place (central docs/ vs local specs/ /), gets committed to the repo, and is never left as a bead comment. Applies to any agent…

not rated 5 today A 84 tokens original MIT

gc-demo-script

03

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Generates a demo:capture-format script from a closed Gas City work bead by reading the bead tree, git commits, and PR diff.

not rated 5 changed 17d ago A SkillSpector: warn 31 tokens original MIT

handoff

04

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when the operator explicitly asks to handoff, reset, wrap up, recycle a session, get fresh context, or restart a coordination agent (mechanik, deacon, witness). Do not invoke from internal judgment that a handoff would be useful — propose it in conversation and let the operator decide.

not rated 5 today A 64 tokens original MIT

learning-distill

05

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The promotion-judgment rubric for the feedback-learning loop — use when you are the mol-feedback-distiller judging pending feedback observations into promotion, retirement, contention, or no proposal at all. This file is the distiller's judgment method, versioned pack content inside the loop it powers — rubric misses…

not rated 5 changed today A SkillSpector: warn 103 tokens original MIT

session-title

06

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when the operator explicitly asks to set, view, suggest, or rotate a title for the current session. Triggers include "rename this session", "rename mechanik", "set my title", "set the title to X", "what's my title", "what's my session title", "suggest a title".

not rated 5 today A 68 tokens original MIT

architect-design

07

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The architect's design method — settle the STRUCTURE of a change or a new system. Use to turn a PRD, a rough idea, or an existing codebase into the architectural decisions that keep implementation coherent: elicit context first, pin only the invariants that would let independently-built parts diverge, and record each…

not rated 5 today A 0 tokens original MIT

architect-review

08

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The architect's review method — assess a proposed change or PRD AGAINST the shape of the system. Use to judge whether a diff, design, or requirements doc respects the system's boundaries and contracts, whether it introduces architectural drift (a structural change that should have updated docs/architecture.md but…

not rated 5 today A 102 tokens original MIT

architect

09

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The architect persona — hold the shape of the system. Use when a change touches system structure (boundaries, contracts, who owns shared data, cross-cutting dependencies), when a PRD or design needs an architectural review, or when you want to reason about the cost of future change. Its methods are the…

not rated 5 today A 88 tokens original MIT

converse-settle

14

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Converse's record, sign-off, and visit close (safety-critical).

not rated 5 changed yesterday A 21 tokens original MIT

review-pm

15

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The method for the PM check — the product lens on a change, reviewed by a peer to the author rather than an order-taker. Judges first whether the change is the right thing for the people the product serves (the outcome its anchor named, not a proxy), then whether the PR lets the operator decide. Grounded in…

not rated 5 changed 9d ago A 129 tokens original MIT

review-triage

16

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The method for the triage check — a broad, cheap scan that does not judge a change but decides which specialist checks it needs, then records that decision by widening the anchor's checkset from the check index's declared checks; and, when bringing the branch current conflicted, rules from the worker's audit on what…

not rated 5 changed today A 125 tokens original MIT

review-arch

17

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The method for the arch check — the Architect, steward and gatekeeper of the repo's high-level architecture. Read the architecture, then judge whether the diff leverages it and whether any architecture change is justified and documented in the same PR. Use when you hold a review bead whose checkname is arch, or when…

not rated 5 changed today A 75 tokens original MIT

review-demo

18

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The method for the demo check, the visual review. Decide whether a change needs a visual to be understood and, when it does, pick the cheapest modality that conveys it (a visual the repo already carries, a screenshot, or a narrated video), deliver it to the PR inline and uncommitted, and record the decision on one…

not rated 5 changed today A 100 tokens original MIT

prs

19

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when something has to happen to an open pull request or its anchor bead. Covers answering its review comments (posting a comment, replying in a thread, resolving a thread), sending it back for rework so its branch changes, holding its merge until something is settled, and retiring it (closing the PR and disposing…

not rated 5 today A 106 tokens original MIT

records

20

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when you need to write down what was decided, what happened, or what a bead needs, so whoever reads it next inherits it. Covers recording an outcome or a finding by appending to a bead's notes, summing up long notes under a Current state heading, and setting the one-line headline the board shows for a bead (its…

not rated 5 today A 100 tokens original MIT

waits

21

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when something must not go yet because it has to wait for other work to land, or for a person to decide or act. Covers making a bead wait on another (blocked by, depends on, after that lands), having a bead close by itself when the work that resolves it lands, instead of coming back to triage (an until edge, for a…

not rated 5 changed today A 166 tokens original MIT

work

22

zookanalytics/gc-toolkit

Skill Claude CodeCodex

Use when you have to say that something needs doing, carry out a decision about who does it, or change work already asked for. Covers filing new work or a follow-up in the right rig and under the right parent (a sibling of the bead that waits on it, or a member of the epic it is part of), sending a bead to a pool on a…

not rated 5 changed today A 168 tokens original MIT

review-correctness

23

zookanalytics/gc-toolkit

Skill Claude CodeCodex

The method for the correctness check, the standing review of whether a change is correct and safe as merged. Read the whole diff, settle its test evidence, work the What to check list, grade every finding P0, P1 or P2, and add the Verification line to the verdict. Use when you hold a review bead whose checkname is…

not rated 5 today A 90 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: