Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/ready)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/ready"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/ready/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/ready"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/ready.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.14566 |
| Opus 5.5 | $0.00051 | $0.05826 |
| Sonnet 5.5 | $0.00025 | $0.02913 |
| Haiku 4.5 | $0.00013 | $0.01457 |
Grade C, and why
ready scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Do not refuse the run, and the reason is the rubric.** `dev-workflows:workflow-states` has rungs How it starts
The opening of the file, as written. The whole thing — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify readiness for AI-driven development: $ARGUMENTS
Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.
/ready is the artifact-anchored readiness gate. Given a PRD or Epic address, it derives the
workflow phase from the artifacts present and checks whether the
ARD/spec/design artifacts that actually exist, taken together, justify that phase and the next
transition, against the rubric in ${CLAUDE_PLUGIN_ROOT}/references/workflow-states.md — and, with
--claimed "<status>", additionally compares the phase the operator declares against the derived one. It returns
SUPPORTED / PARTIAL / NOT-SUPPORTED with a requirement coverage roll-up and named gaps, gated on
the Opus readiness-reviewer.
Key distinction from every other pipeline command: /ready authors nothing in the PRD/Epic/ARD/spec/design sense — it never writes any of those, and it never writes a status. Its only authored write is an overwritten _readiness.md snapshot under $SPECS_PATH, and it branches only via the workflows-core:phase-handoff §4.3 consent choice to hand that snapshot off, creating ready/<KEY>-<slug> — specs-preflight itself still creates none, switching $SPECS_PATH only between branches that already exist and are plugin-created (workflows-core:specs-repo-git §2.2). _readiness.md is likewise committed only through that same §4.3 choice, never automatically — declining leaves it uncommitted; the terminal commit-artifacts step commits ONLY the run's bounded session-artifact paths (workflows-core:specs-repo-git §2.1), which _readiness.md is not. Where /design's repo gate is a strict, hard-stop mount check because it is about to ground code decisions, /ready's repo check is best-effort presence only — it never scans code, it only notes whether a needed repo is mounted.
Key distinction from every other consumer of workflows-core:phase-handoff §3 (require-on-main) and workflows-core:ard-resolution: every other caller's own gate stops it when a gated ARD/spec/design resolves off the specs repo's default branch (/product-workflows:brd-reconcile reads a stopping row without stopping at two sites and never at its ordinary Phase 0 gate — its cross-BRD write guard, and a --sent run's redundancy check at Phase 0 step 6, which reads the gate inverted; phase-handoff §3.7 names both); /ready never stops. That state becomes a readiness finding — "authored but not handed off" — that caps the eventual verdict at PARTIAL; an artifact that is absent outright is recorded as missing in the coverage roll-up, exactly as before this feature. Reporting readiness is /ready's whole function, so a run that stops instead of reporting has failed at the one thing it exists to do.
Key distinction from /design's Epic-picker behavior: a PRD- address is a first-class
PRD-level check (workflow-states.md's PRD ladder), not something that must be resolved down to a
single Epic. Address an EPIC- folder to scope the check to one Epic
(the Epic ladder) instead.
Phase 0 — Resolve input
- Resolve the address. Parse the single positional address from
$ARGUMENTS— a<KEY>, or an@<path>naming a folder or a file inside one — and resolve it withresolve-address(Skill(skill: "workflows-core:reference", args: "addressing resolve-address"), §3).status: found→ carry itspath,kindandkeyforward;ambiguous→ stop, naming every match.absentis a stop, not a folder to create — this command creates no folder in the specs tree. Surface thekey dir not foundrule inSkill(skill: "workflows-core:reference", args: "escalation-rules")(choices: ["Re-enter key", "Cancel"]) and name what does create one: aPRD-folder comes from/product-workflows:idea <KEY>or/product-workflows:create-prd <KEY>on the idea route and from/product-workflows:brd-spliton its parent BRD on the BRD route; anEPIC-folder comes from/product-workflows:epics <PRD-ADDRESS>and from no other command.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago Changed · +3 lines b048274ea925
- 24d ago Changed · +46 lines 1a77ea7ed915
- 28d ago Changed · +7 lines 123f90e2b442
- 1mo ago Changed · +26 lines scan A → C 0a5d879d3bef
- 1mo ago First seen · 638 lines · 127 tokens per session scan A 12c2812e57a4
ready is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 24d ago), licensed MIT. It adds 127 tokens to every session and 14,566 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
brainstorm
Brainstorm product ideas or experiments from PM, Designer, and Engineer perspectives — for existing or new products.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
ralph
Ralph autonomous development loop with fresh context per iteration.
plan
Hierarchical planning entry point — all 11 plan verbs in one command. v3.7.2 consolidates /aura-frog:plan- (10 commands) into a single dispatcher that routes via the plan-orchestrator skill. The legacy plan- aliases still work as thin stubs.
frankx-ai-build
Comprehensive FrankX.AI website build session - plan, create, review, deploy.