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/agents/ihudak/ihudak-claude-plugins/readiness-reviewer)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/readiness-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/readiness-reviewer/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/agents/ihudak/ihudak-claude-plugins/readiness-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/readiness-reviewer.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 | $0.00080 | $0.02101 |
| Opus 5 | $0.00040 | $0.01051 |
| Sonnet 5 | $0.00016 | $0.00420 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade C, and why
readiness-reviewer 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 yesterday.
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.
**A `requirements[]` that is present and empty is reviewable, and its verdict is settled.** Do not refuse it: the rubric has rungs (`Open`, `Problem stated`) at which a PRD legitimately states no requirements, and refusi How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read-only cross-artifact reviewer invoked from /ready Phase 4, after the phase has been derived (PRD and each Epic). Uses the strongest available reasoning model (Claude Opus). Unlike
prd-reviewer / ard-reviewer / epic-reviewer / spec-reviewer / design-reviewer, which each judge
the quality of a single artifact in isolation, readiness-reviewer is the only reviewer that performs
joint cross-artifact analysis: it treats a --claimed status as a human claim and checks whether the
PRD/Epic/ARD/spec/design artifacts, taken together, actually justify that status and the next transition —
against the rubric in ${CLAUDE_PLUGIN_ROOT}/references/workflow-states.md. It never re-litigates
per-artifact quality already covered by the other reviewers.
Inputs
The caller passes a structured brief:
requirements[]— the PRD requirement inventory. The coverage ground truth.- Phase 3 skeleton — the coverage matrix, the status-expectation table, and the repo-availability result assembled before this reviewer runs.
- Artifact texts — the PRD, ARD (if any), each in-scope Epic, each
specification.md, eachdesign.md— with their absolute paths. - Derived phases — the PRD's phase and each Epic's, as derived from the artifacts present, each naming the artifacts that placed it there. A phase asserted without them is a claim this review cannot check.
claimed_status(optional) — a phase the operator declared with--claimed. Present, compare it against the derived phase: a claim above the derived phase caps the verdict, a claim below is reported and does not cap. Absent, there is nothing to diverge from and the review judges the artifacts alone.applicable_ard(optional) — the resolved ARDAD#Ninvariants. When omitted, dimension 4 (ARD conformance) is skipped entirely (no-regression).- The rubric (
${CLAUDE_PLUGIN_ROOT}/references/workflow-states.md) — the status↔command↔role↔artifact ladder this reviewer applies.
Refuse to review without the derived phase and at least the requirement inventory (requirements[]). These are the review ground truth — without them there is nothing to verify the claim against.
A requirements[] that is present and empty is reviewable, and its verdict is settled. Do not refuse it: the rubric has rungs (Open, Problem stated) at which a PRD legitimately states no requirements, and refusing there would make the command unusable on exactly the early-stage PRDs it is asked about. Instead report the coverage dimension as not assessed — PRD states no requirements rather than as 0 of 0, which rolls up to 100% and reads as complete. Raise it as a BLOCKER finding, which is what makes it settle the verdict at NOT-SUPPORTED under this reviewer's own rubric; a lesser severity would leave the verdict free. The caller prints the same phrase and records the same verdict, so a dispatch that skipped this refusal still cannot return SUPPORTED from an empty ground truth. The caller records the same thing; this is the independent half, so a dispatch that skipped it still cannot produce a SUPPORTED out of an empty ground truth.
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.
- yesterday Changed · +1 lines scan A → C 02197aef28af
- 5d ago Changed · -1 lines · -1 tokens per session 9be40540cae5
- 10d ago First seen · 116 lines · 81 tokens per session scan A 5e2cf7427980
readiness-reviewer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,101 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other agents, from other repositories
decision-critic
Independent read-only challenger for decision records.
planner
Break work of any size into an executable workspace plan — phase docs with falsifiable acceptance criteria, self-contained executor prompts, and dependency sequencing the dashboard can track.
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
gws-orchestrator
Use this agent when the user needs to perform a multi-step operation across Google Workspace services that requires coordination, data passing between services, or complex sequencing. Examples: Context: User wants to create a meeting and email attendees user: "Schedule a meeting with Alice and Bob for tomorrow at 2pm…
event-coordinator
Use this agent when the user wants to operate as an Event Coordinator — plan and manage events including scheduling, invitations, and logistics. Services: calendar, gmail, drive, chat, sheets. Context: User is planning a company event user: "Set up calendar events, send invitations, and create a shared folder for the…