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/allisoneer/agentic_auxilaryWrote 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/allisoneer/agentic_auxilary/review)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/review"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/review/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/allisoneer/agentic_auxilary/review"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/review.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 | $0.00008 | $0.02360 |
| Opus 5.5 | $0.00003 | $0.00944 |
| Sonnet 5.5 | $0.00002 | $0.00472 |
| Haiku 4.5 | $0.00001 | $0.00236 |
Grade A, and why
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 1mo 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraints:
- Sub-agents have NO git access and NO bash access.
- Diff content is embedded in the reviewer prompt (fileless operation).
- You (main agent) call
review_diff_snapshotto generate a cached diff, thenreview_runfor each lens.
Default output behavior:
- Show only Medium+ severity findings.
- If Low severity findings exist, hide them by default and report "hidden_low_count".
- If the user asks for a more exhaustive/pedantic pass (e.g., "include nits" or "include low severity"), include Low severity findings too.
You MUST follow ALL 6 steps EXACTLY.
Interpret Intent (Free-text)
Interpret $ARGUMENTS as a natural-language request. Do NOT require or advertise any special syntax.
Resolve these internal parameters (used in later steps):
- mode: default | staged
- paths: [...]
- include_nits: true/false
- focus: "..."
Smart defaults if the user doesn't specify:
- mode=default (review all local changes)
- paths=[] (no path restriction)
- include_nits=false (hide Low severity; still report hidden_low_count)
- focus="" (no extra focus weighting)
Examples of what the user might say (illustrative only, not required formats):
- "review my changes"
- "review just the staged changes"
- "review src/auth.rs and src/db/; focus on error handling"
- "be pedantic and include nits"
How to infer intent:
- Set mode=staged when the user asks for "staged", "index", or "only what's been added"
- Populate paths when the user explicitly names file/dir paths
- Prefer NOT restricting paths unless the user is explicit; if ambiguous, treat it as focus instead
- Set include_nits=true when the user asks to "include nits", "include low severity", "be exhaustive/pedantic", or similar
- Treat any remaining free-form request as focus (e.g., "focus on security", "focus on edge cases")
Ambiguity policy (match /review_pr_comments pattern):
- Only ask a clarifying question if intent is truly ambiguous and a wrong assumption would materially change review scope.
- Otherwise proceed with defaults and disclose assumptions in the final chat response (Step 6).
Record the resolved parameters explicitly (and note any assumptions for Step 6 disclosure).
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.
- 1mo ago First seen · 282 lines · 8 tokens per session scan A 0ac9234c8759
review is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 8 tokens to every session and 2,360 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
factory
Linha de montagem multi-agente (Software Factory) — spec-writer → builder em worktree isolado → 4 revisores paralelos (Security, Code, UI, UX) → approver com gate de risco e dashboard visual.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
release-tag
Create and push a version tag after a release PR has been merged.