Scouted it, wrote it in the roadbook, lost the pencil. It keeps your plan as a map of what waits on what. Roadbooks as a dependency graph: JSON source of truth, mechanical status recompute, projected waypoint lists, Mermaid diagrams, an HTML chart, the interview, review and next-waypoint skills that drive it, and /scout-waypoints, a pane that shows the ready waypoints and starts a trail on one.
roadmap
JasonWarrenUK/goblin-mode
Roadmaps as a dependency graph: JSON source of truth, mechanical status recompute, projected task lists, Mermaid diagrams, an HTML dashboard, the interview, review and next-task skills that drive it, and /ready, a pane that shows the ready set and claims a task.
vellum
bengous/claude-code-plugins
Plan at the frontiers and review the plan in the browser: decisions and interfaces before mechanics, vertical slices each closed by a check. /vellum:start opens a planning mode of its own: Claude writes the plan and its mockups and grills the reviewer on the open choices; the reviewer comments, edits or approves in a page, and the answer reaches Claude as a prompt.
inline-images
Mechazawa/claude-inline-images
Gives Claude a show_image tool and shows pasted images and images Claude reads inline in the terminal transcript
proctor
nalyk/nalyk-skills
Hook-enforced development discipline for Claude Code. Skills teach methodology; hooks enforce compliance mechanically (git gates, planning mode, step budgets, quiet mode, pre-flight checks, self-diagnosis, autonomy metrics); store + tracing survive compaction.
agent-cross-check
naoanao/agent-cross-check
When another coding agent (or a person) commits to your repo, Claude notices, runs mechanical checks (line endings, secrets, .env files, and the agent's report against the real files: missing files, silent videos, unconfirmed claims) and audits the commits by diff and tests. A git push waits until they are reviewed.
delegate
HarzerHeribert/claude-modpack
A hand_off tool: Claude gives a self-contained task to a cheaper worker model (Haiku for lookups and mechanical changes, Sonnet for build work) that stays warm between tasks, with where the change reaches from the language server, the diff and a check run by the tool as evidence, a review by the main model, and a log of what it saved and how often the work came back.