iterative-development
An iterative implementation methodology that pairs with superpowers. Extracts requirements with proof obligations from large spec collateral, defines a walking skeleton that closes a real journey, then loops through audited sprints building a behavior evidence corpus until an auditor confirms the product matches the spec. Designed for comprehensive or ambiguous specs where the upfront writing-plans flow loses the plot.
pinned to #c05889aupdated 3 months ago
Ask your AI client: “install plugins/iterative-development”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install plugins/iterative-developmentmetahub onboarded this repo on the author's behalf.
If you own github.com/prime-radiant-inc/iterative-development on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
139
Last commit
3 months ago
Latest release
published
- #ai-agents
- #autonomous-agents
- #claude-code
- #claude-code-plugin
- #methodology
What's bundled
Items extracted from this plugin's manifest + directory tree.
Skills (7)
skills/auditing-progressUse when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel co…skills/extracting-requirementsUse when starting an iterative-development run on human spec collateral — reads the spec, produces per-epic requirement files with proof obligations and behavior scenario cards with stable IDs.skills/implementing-tasksUse when executing a batch of TDD-sized tasks inside a running-an-iteration call — dispatches an implementer subagent per task following red-green-refactor discipline and returns per-task completio…skills/iterative-developmentUse when implementing a project with a large, comprehensive, or ambiguous spec — extracts requirements with proof obligations, defines a walking skeleton with its first journey scenario, then loops…skills/running-an-iterationUse when executing the next pending iteration from an iterative-development roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches impleme…skills/scoping-the-simplest-coreUse when turning extracted requirements into a roadmap — selects the walking skeleton iteration with its first journey scenario, orders remaining work into follow-on iterations, and applies story s…skills/shared
Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.c05889a· 3 months ago
Behavioral checks ran but aren't published for this artifact; the static checks above ran at publish time.
Maintenance
2 passed1 warningCI configuration detectedwarn
no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)
Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.
Recent activity
last push 4 weeks ago
Tests detected
1 test directory · 6 test files
Release history
1- releasecurrentc05889awarn3 months ago
Contents
A Claude Code plugin that drives an autonomous, audited implementation loop for projects with large, comprehensive, or ambiguous specs. Pairs with superpowers.
When to use it
Use this plugin when:
- Your spec is large, comprehensive, or ambiguous (10+ files, 100+ requirements).
- You want the product in a working, testable state at every iteration boundary.
- You want an autonomous audited loop rather than a single upfront plan.
- The
superpowers:writing-plans→superpowers:subagent-driven-developmentflow has lost the plot on this project before.
Do not use it for small, bounded projects — superpowers:writing-plans is simpler and more appropriate.
What it does
The top-level iterative-development skill orchestrates the full lifecycle:
- Extract requirements — chunks the spec, dispatches parallel extraction subagents, and produces stories with proof obligations plus behavior scenarios. Aggregates into per-epic files, a behavior-scenarios corpus, and a coverage ledger.
- Scope the simplest core — defines the walking skeleton iteration (ITER-0000) and an ordered roadmap of follow-on iterations. The walking skeleton must close at least one real journey scenario, not just compile.
- Run iterations — sentinel baseline → scope review → decompose code + evidence tasks → implement → impacted + sentinel scenario runs → wrap up.
- Audit progress — paired auditors run a three-tier review (deep evidence, impacted behavior, sentinel corpus) using parallel adversarial review (PAR). Gaps feed back into the backlog.
- Terminate — when the roadmap is drained and a final behavior-evidence audit passes, the loop exits.
Completion means the product has passing behavior evidence at the correct seam for every externally observable requirement — not just that stories are marked done.
Skills
| Skill | Role |
|---|---|
iterative-development | Top-level orchestrator for the autonomous loop. |
extracting-requirements | Chunk + parallel-extract + aggregate stories and scenarios from spec collateral. |
scoping-the-simplest-core | Define walking skeleton and roadmap. |
running-an-iteration | Execute one sprint end-to-end. |
implementing-tasks | Per-task implementer with evidence discipline. |
auditing-progress | PAR-based audits at iteration and corpus level. |
Installation
Install from the Prime Radiant marketplace:
/plugin marketplace add prime-radiant-inc/prime-radiant-marketplace
/plugin install iterative-development@prime-radiant-marketplace
Restart Claude Code after installing.
Running the tests
./scripts/run_validation_suite.sh
Individual test files can be run with pytest tests/.
Relationship to superpowers
This plugin depends conceptually on skills from the superpowers plugin (brainstorming, TDD, parallel adversarial review, verification-before-completion). Install superpowers alongside iterative-development for the intended experience.
License
Apache License 2.0. See LICENSE.
Reviews
No reviews yet. Be the first.
Related
ponytail
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
ECC
Harness-native ECC plugin for engineering teams - 63 agents, 249 skills, 79 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Claude Mem
Memory compression system for Claude Code - persist context across sessions
mh install plugins/iterative-development