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/Ingramradical235/anty-frameworkWrote 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/ingramradical235/anty-framework/review)<a href="https://agentmods.dev/commands/ingramradical235/anty-framework/review"><img src="https://agentmods.dev/badge/commands/ingramradical235/anty-framework/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 | $0.00012 | $0.01530 |
| Opus 5 | $0.00006 | $0.00765 |
| Sonnet 5 | $0.00002 | $0.00306 |
| Haiku 4.5 | $0.00001 | $0.00153 |
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 7d 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.
This is a copy
100% identical to review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anty:review — 5-Question Review Engine
Trigger
User runs /anty:review
Behavior
Execute the 5-question review engine using the Analyst subagent (agents/analyst.md). Evaluate in strict priority order, proceeding deeper only if the answer to each question is "yes". Surface the level where the problem is.
Agent
Use the Analyst subagent for all evaluation steps.
The 5 Questions (Strict Priority Order)
Question 1: WHERE — Has the Goal progressed since last review?
Read .anty/goals/*.yaml and .anty/history/scans/*.yaml.
- Compare current goal metric to last review's metric
- Calculate absolute and percentage change
- Check if progress rate is sufficient to reach target within timeline (including buffer)
Display:
Q1: Has the Goal progressed since last review?
----------------------------------------------------
Goal: [goal name]
Last review: [metric value] ([date])
Current: [metric value] ([date])
Change: [+/- delta] ([+/- %])
On track: [yes/no — based on required run rate]
----------------------------------------------------
If NO (goal has not progressed): STOP HERE. The problem is at the WHERE level.
- Diagnosis: Goal is not moving. No further investigation needed until progress resumes.
- Recommend: Review which Drivers should be generating movement.
- Skip Q2-Q5.
If YES: Proceed to Q2.
Question 2: Execution — Were approved Actions executed as planned?
Read .anty/actions/*.yaml — check actions with status approved or in_progress.
- Compare planned steps vs completed steps for each action
- Check if execution timeline matches planned timeline
- Identify any actions that were approved but not started
- Identify partially completed actions
Display:
Q2: Were approved Actions executed as planned?
----------------------------------------------------
Action: [action name]
Planned steps: [n] | Completed: [m] | Status: [status]
Timeline: [on-time / delayed by N days]
...
Overall execution rate: [completed/planned] ([%])
----------------------------------------------------
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.
- 7d ago First seen · 198 lines · 12 tokens per session scan A 27889b9effd2
review is a command published in the GitHub repository Ingramradical235/anty-framework (1 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 1,530 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to review, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
plan
/anty:plan — Strategy Kernel Generation.
actions
/anty:actions — 3-Option Choice Approval with Nudge Architecture.
onboard
/anty:onboard — QUEST-Based Conversational Interview.
quickstart
/anty:quickstart — 5-Minute Quick Onboarding to First Action.
review
/anty:review — 5-Question Review Engine.
scan
/anty:scan — Analysis Cycle (10-Point).