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/OXI-717/ai-native-toolkitWrote 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/oxi-717/ai-native-toolkit/team-review)<a href="https://agentmods.dev/commands/oxi-717/ai-native-toolkit/team-review"><img src="https://agentmods.dev/badge/commands/oxi-717/ai-native-toolkit/team-review.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.05922 |
| Opus 5 | $0.00009 | $0.02961 |
| Sonnet 5 | $0.00004 | $0.01184 |
| Haiku 4.5 | $0.00002 | $0.00592 |
Grade A, and why
team-review 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 8d 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 — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teams-based Code Review with Fix Loop
Run a comprehensive code review, automatically fix all issues found, verify fixes with build/test, and re-review until clean. Fully autonomous by default — no user confirmation needed.
Full Cycle
┌─────────────────────────────────────────────────────┐
│ MULTI-REPO: if changes in multiple repos detected, │
│ iterate each repo through PHASE 1-5 autonomously │
├─────────────────────────────────────────────────────┤
│ PHASE 1: REVIEW │
│ Parse scope → Gather diff → Spawn review agents │
│ → Confidence scoring → Report │
├─────────────────────────────────────────────────────┤
│ PHASE 2: FIX (if issues found) │
│ Ask user → Spawn fixer agent → Apply fixes │
├─────────────────────────────────────────────────────┤
│ PHASE 3: BUILD & TEST │
│ Detect build system → Run build → Run tests │
├─────────────────────────────────────────────────────┤
│ PHASE 4: RE-REVIEW │
│ Quick review of fixes only → Verify no regressions │
│ → If new issues → back to PHASE 2 (max 3 loops) │
├─────────────────────────────────────────────────────┤
│ PHASE 5: FINAL REPORT & CLEANUP │
│ Summary of all iterations → Shutdown team │
└─────────────────────────────────────────────────────┘
Arguments
Input: $ARGUMENTS
Flags:
--ask— Ask user after review whether to fix (interactive choice)--no-fix— Review only, no fix loop (report and stop)- Default (no flag): auto-fix all found issues without asking
AUTONOMOUS MULTI-REPO BEHAVIOR
This is NOT a separate phase — it's a behavioral rule for the agent.
When during scope detection you discover changes span multiple repositories (e.g. you checked git status and found unpushed commits in several sibling repos), you MUST:
- Never ask the user which repo to review — review ALL of them automatically
- Never say "too many changes, pick one" — handle the volume yourself
- Sort repos by change count (ascending) and iterate from smallest to largest
- Run the full PHASE 1 → PHASE 5 cycle independently for each repo
- Report progress as you go:
"--- Reviewing [repo-name] ([N changes]) ---"
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.
- 8d ago First seen · 584 lines · 18 tokens per session scan A 33980fc4559b
team-review is a command published in the GitHub repository OXI-717/ai-native-toolkit (8 stars, last pushed 16d ago), licensed MIT. It adds 18 tokens to every session and 5,922 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 2026-08-31.
Other commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.