dcosson/h2

An agent runner, messaging, and orchestration layer.

This repository also configures its own agents. See what h2 tells them →

163Stars on the repository
19Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

babysit-pr

01

dcosson/h2

Skill Claude Code

Schedule yourself to wake up every 5 minutes and shepherd an open PR — fix failing CI, address review-bot comments (push fixes for legit findings, resolve false positives, re-request review once addressed), reply to mechanical human comments with fixes, and flag architecture-level human comments back to the user.…

not rated 163 +2 yesterday A SkillSpector: warn 84 tokens original MIT

dcosson/h2

Skill Claude Code

Incorporate code review feedback — make code changes, commit with review trailers, update disposition table, and request re-review if needed. Mirrors plan-incorporate for code reviews.

not rated 163 +2 yesterday A SkillSpector: pass 42 tokens original MIT

code-review

03

dcosson/h2

Skill Claude Code

Review a code diff for a bead/feature. Produces a structured review doc with severity-rated findings. Run by reviewer agents after implementation is complete.

not rated 163 +2 yesterday A SkillSpector: pass 33 tokens original MIT

e2e-wiring-review

04

dcosson/h2

Skill Claude Code

End-to-end wiring audit of a component or application. Traces every user-facing entry point through the full request path, identifies what is wired vs stubbed/dead, and verifies test coverage. Works for any project type — web apps, APIs, CLIs, databases, mobile apps.

not rated 163 +2 yesterday A SkillSpector: pass 65 tokens original MIT

plan-architect

05

dcosson/h2

Skill Claude Code

Produce a high-level architecture doc and — if the project is large enough — a plan index that lists sub-plans to be written later. Use after shaping to create the planning structure. Does NOT write sub-plans itself.

not rated 163 +2 yesterday A SkillSpector: pass 49 tokens original MIT

plan-draft

06

dcosson/h2

Skill Claude Code

Write a detailed plan doc and its companion test harness doc for a single component. Use after plan-architect has created the plan index.

not rated 163 +2 yesterday A SkillSpector: pass 31 tokens original MIT

plan-incorporate

07

dcosson/h2

Skill Claude Code

Incorporate review feedback into a plan doc. Reads review files, updates the source doc, adds a disposition table tracking every finding, and deletes review files. Supports multiple review rounds — detects existing disposition tables and adds the next round.

not rated 163 +2 yesterday A SkillSpector: warn 52 tokens original MIT

plan-orchestrate

08

dcosson/h2

Skill Claude Code

Orchestrate the full planning lifecycle — from input assessment through architecture, plan writing, review cycles with convergence, and sign-off. Designed for concierge/scheduler agents coordinating multi-agent planning work.

not rated 163 +2 yesterday A SkillSpector: pass 43 tokens original MIT

plan-review

09

dcosson/h2

Skill Claude Code

Independently review a plan doc and its test harness. Produces a review findings doc rated P0-P3. Run multiple times with different reviewers for independent perspectives.

not rated 163 +2 yesterday A SkillSpector: pass 37 tokens original MIT

plan-seam-review

10

dcosson/h2

Skill Claude Code

Review the interfaces and seams between connected plan components to catch wiring omissions before implementation begins. Runs after individual plan reviews converge, before plan-to-beads. Supports vertical-slice (end-to-end request path) and horizontal-seam (cross-cutting contract) review modes.

not rated 163 +2 yesterday A SkillSpector: pass 59 tokens original MIT

plan-summarize

11

dcosson/h2

Skill Claude Code

Generate a planning summary doc with review statistics, incorporation rates, convergence tracking, finding patterns, and document metrics across plan docs AND test harness docs. Supports multiple review rounds — each round gets its own section.

not rated 163 +2 yesterday A SkillSpector: pass 46 tokens original MIT

plan-tighten

12

dcosson/h2

Skill Claude Code

Surgically trim verbosity and within-doc duplication from a plan doc without losing fidelity. Cuts review residue, restated rationale, illustrative code that prose+signature already covers, redundant adjacent sections, and prose-then-table restatements. Preserves all API/interface specs, acceptance criteria, URP/EO/AA…

not rated 163 +2 yesterday A SkillSpector: pass 95 tokens original MIT

plan-to-beads

13

dcosson/h2

Skill Claude Code

Decompose reviewed plan docs into implementation beads (epics + tasks) with correct dependencies. Reads plan docs, identifies components, and creates properly sized bd tasks.

not rated 163 +2 yesterday A SkillSpector: warn 37 tokens original MIT

dcosson/h2

Skill Claude Code

Verify implemented plan docs against their actual code, add completion signoff metadata, and surface any gaps as new beads. Designed for scheduler/concierge agents coordinating multi-agent signoff after implementation is done.

not rated 163 +2 yesterday A SkillSpector: pass 47 tokens original MIT

prepare-to-land

15

dcosson/h2

Skill Claude Code

Clean up a long-running work branch before landing into main — close beads, prune review docs, strip ceremonial comments, undo accidental cross-cutting refactors that weren't part of the task. Run after implementation completes, before opening the PR to main. Specific to the final land into the trunk, NOT for ordinary…

not rated 163 +2 yesterday A SkillSpector: pass 73 tokens original MIT

shaping

16

dcosson/h2

Skill Claude CodeCodex

Use this methodology when collaboratively shaping a solution with the user - iterating on problem definition (requirements) and solution options (shapes).

not rated 163 +2 yesterday A SkillSpector: pass 30 tokens original MIT

stress-test

17

dcosson/h2

Skill Claude Code

Adversarially stress-test a technical plan by verifying claims against real docs, running POC code, and updating the plan before you build.

not rated 163 +2 yesterday C 32 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: