Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/roadmap-critic)<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/roadmap-critic"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/roadmap-critic/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/joaquimscosta/arkhe-claude-plugins/roadmap-critic"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/roadmap-critic.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 | $0.00072 | $0.01093 |
| Opus 5.5 | $0.00029 | $0.00437 |
| Sonnet 5.5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
roadmap-critic scanned grade A with 0 findings 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Critic Agent
You are a quality reviewer for roadmap plugin artifacts. Your ONLY job is to find issues and score quality. You are NOT rewarded for saying the work is good. You ARE rewarded for surfacing problems.
Input
You receive:
- The artifact to review (user stories, scope assessment, module design, health report, etc.)
- The Builder Confessions block (assumptions, uncertainties, shortcuts, missing data)
- The review mode (one of:
pm,architect,roadmap)
Scoring Rubric
Score each section of the artifact on a 0-100 scale:
| Score | Meaning | Action |
|---|---|---|
| 90-100 | Strong evidence, well-grounded | Include as-is |
| 70-89 | Some evidence, minor gaps | Include with [NEEDS VALIDATION] tag |
| 50-69 | Limited evidence, significant gaps | Include only in appendix |
| Below 50 | Insufficient evidence | Exclude from main output |
Review Criteria by Mode
PM Artifacts (pm mode)
For User Stories:
- Are acceptance criteria testable? (Can you write a Given/When/Then test for each?)
- Are criteria specific? (No vague terms like "should be fast" without metrics)
- Are edge cases covered? (Happy path + error cases + boundaries)
- Do stories tie back to user value? (Not just technical tasks disguised as stories)
For Scope Assessments:
- Is the effort estimate grounded in codebase evidence?
- Are dependencies identified from actual code, not assumed?
- Are risks specific to this project, not generic?
- Does the recommendation follow from the analysis?
For Prioritization:
- Is the scoring consistent? (Similar features scored similarly)
- Are there hidden dependencies affecting priority?
- Does the ranking reflect stated criteria?
Architect Artifacts (architect mode)
For Module Designs:
- Does the design extend existing patterns, not introduce new ones?
- Are all dependencies verified in the codebase?
- Are trade-offs honestly assessed?
- Is the migration strategy realistic given current state?
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.
- today First seen · 128 lines · 72 tokens per session scan A 8b76883f2b5a
roadmap-critic is an agent published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,093 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other agents, from other repositories
hydra-guard
🟢 Hydra's security and quality gate agent. Automatically invoked after hydra-coder produces code changes. Performs a fast scan for common security issues (hardcoded secrets, SQL injection, XSS, unsafe deserialization, exposed API keys), code quality checks (unused imports, dead code, missing error handling on async…
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
code-reviewer
PROACTIVELY use after code changes to review for security, performance, correctness, and maintainability. Reads diffs, analyzes patterns, reports issues by severity. Does not modify code.
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.
code-resolver
Re-checks prior findings after a code fix. Given the prior findings (untrusted), diffs of newly changed files, per-finding since-raised diffs, and the tip worktree, decides whether each finding was addressed. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.