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.
npx agentmods add commands/ambient-code/agentready/review-agentreadygit clone --depth 1 https://github.com/ambient-code/agentreadyWhat 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 | $0.00012 | $0.01623 |
| Opus 5 | $0.00006 | $0.00812 |
| Sonnet 5 | $0.00002 | $0.00325 |
| Haiku 4.5 | $0.00001 | $0.00162 |
Grade A, and why
review-agentready 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 2d 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.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provide an AgentReady-specific code review for the given pull request.
This command extends the standard /code-review with agentready project-specific concerns:
- Map findings to the 25 agentready attributes (from agent-ready-codebase-attributes.md)
- Calculate impact on self-assessment score (current: 80.0/100 Gold)
- Generate remediation commands (agentready bootstrap, black, pytest, etc.)
- Link to relevant CLAUDE.md sections
- Categorize by severity with confidence scoring
Process
Follow these steps precisely:
-
Eligibility Check (Haiku agent)
- Check if PR is closed, draft, or already reviewed
- Skip if automated PR (dependabot, renovate) unless it touches assessors
- If ineligible, exit early
-
Context Gathering (Haiku agent)
- List all CLAUDE.md files (root + modified directories)
- Get full PR diff and metadata
- Return concise summary of changes
-
Parallel AgentReady-Focused Review (5 Sonnet agents) Launch 5 parallel agents to independently review:
Agent #1: CLAUDE.md Compliance Audit
- Check adherence to CLAUDE.md development workflows
- Verify pre-push linting (black, isort, ruff)
- Verify test requirements (pytest, >80% coverage)
- Check branch verification, conventional commits
Agent #2: AgentReady-Specific Bug Scan Focus on agentready assessment logic:
- TOCTOU bugs in file system operations
- AST parsing correctness (false positives/negatives in assessors)
- Measurement accuracy issues
- Type annotation correctness
- Error handling patterns (try-except, graceful degradation)
Agent #3: Historical Context Analysis
- Read git blame for modified assessor files
- Check for regression in assessment accuracy
- Verify attribute scoring logic hasn't changed unintentionally
Agent #4: Previous PR Comment Analysis
- Review comments on past PRs touching same files
- Check for recurring issues
Agent #5: Code Comment Compliance
- Verify changes follow inline comment guidance
-
Attribute Mapping (Haiku agent for each issue) For each issue found:
- Map to specific agentready attribute ID (e.g., "2.3 Type Annotations")
- Determine tier (1=Essential, 2=Critical, 3=Important, 4=Advanced)
- Calculate score impact using tier weights (Tier 1: 50%, Tier 2: 30%, etc.)
- Generate remediation command (black, pytest, agentready bootstrap --fix)
- Link to CLAUDE.md section
-
Confidence Scoring (parallel Haiku agents) For each issue, score 0-100 confidence:
- 0: False positive
- 25: Might be real, unverified
- 50: Verified but minor
- 75: Very likely real, important
- 90: Critical issue (auto-fix candidate)
- 100: Blocker (definitely auto-fix)
Critical Issue Criteria (confidence ≥90):
- Security vulnerabilities (path traversal, injection)
- TOCTOU race conditions
- Assessment accuracy bugs (false positives/negatives)
- Type safety violations causing runtime errors
- Missing error handling leading to crashes
-
Filter Issues
- Keep issues with confidence ≥80 for reporting
- Flag issues with confidence ≥90 as "auto-fix candidates"
- Calculate aggregate score impact
-
Final Eligibility Check (Haiku agent)
- Verify PR is still eligible for review
- Check if PR was updated during review
-
Post Review Comment (using gh pr comment) Use the custom AgentReady format (see below)
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.
- 2d ago First seen · 193 lines · 12 tokens per session scan A da7f500e3663
review-agentready is a command published in the GitHub repository ambient-code/agentready (151 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 1,623 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
run
The universal entry point. Type /run and Aura Frog auto-detects intent: feature, bugfix, refactor, test, deploy, review — then runs the right flow.
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.
extend
Create project-level skills / rules / commands. Always writes to .claude/ in the user's project — NEVER to the plugin's aura-frog/ folder.
dashboard
CLI status display — terse one-screen view of plan tree, active task, conflicts, freezes, token budget, recent decisions.
heal
Self-healing orchestration. Diagnose F2/F3 failures, view proposals, accept/decline, disable.
mcp
MCP security operations. Status, audit, rate-limit reset, connectivity test.