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 skills add VoxTechnologies/anty-framework --skill choice-architecturegit clone --depth 1 https://github.com/VoxTechnologies/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/skills/voxtechnologies/anty-framework/choice-architecture)<a href="https://agentmods.dev/skills/voxtechnologies/anty-framework/choice-architecture"><img src="https://agentmods.dev/badge/skills/voxtechnologies/anty-framework/choice-architecture.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 | $0.00072 | $0.01489 |
| Opus 5 | $0.00036 | $0.00745 |
| Sonnet 5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
choice-architecture 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- choice-architecture — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choice Architecture (Nudge Design)
When to Apply
- Presenting 3-option Action proposals
- Designing any choice flow for the founder
- Post-choice reinforcement moments
- Session opening and closing design
- Any time the founder makes a decision through the system
Core Framework
Smart Default vs Active Choice
Auto-select presentation mode based on data confidence:
Mode A — Smart Default (segment data sample >= 20):
[selected] Option B: LinkedIn DM, casual, 10 CTOs <- RECOMMENDED
"Based on 340 similar actions: 28% avg response."
[ ] Option A: Email sequence, professional, 50 leads
[ ] Option C: Twitter thread, thought-leadership
Pre-selected default. One tap to proceed.
Non-recommended options: one deliberate extra step (good sludge).
Mode B — Active Choice (sample < 20 or high preference diversity):
( ) Option A ( ) Option B ( ) Option C
"I don't have enough data to recommend one. This is your call."
Threshold: segment data sample >= 20 triggers Smart Default.
Outcome Mapping (Attribute -> Experienced Result)
Translate abstract attributes to concrete experiential outcomes:
Instead of (attribute-based):
"Email sequence, professional tone, 50 leads, this week"
Show (outcome-mapped):
"In 2 weeks: ~5 replies, ~1 demo booking.
Cost: $2.95. Your time: 30 min to review drafts."
Projections from segment benchmarks + user's historical performance.
Channel Factors (Concrete Next Step per Option)
Each option includes a single specific next action with time/place:
Option A -> "Review 3 email drafts by Thursday 5pm"
Option B -> "Approve 10 DM messages now (2 min)"
Option C -> "Review thread outline tomorrow morning"
Converts the choice UI from decision-point into action-trigger.
RECAP (Founder's Own Data Before Choices)
Surface the founder's behavioral context BEFORE presenting options:
"Your context for this decision:
- Last 4 weeks: 8h on outreach, 2h on content
- LinkedIn response rate: 22% (above segment avg 18%)
- Email response rate: 4% (below segment avg 8%)
- Burn rate: $12K/mo | Runway: 14 months
- Current constraint: Demo capacity (2/week max)
Given this context, here are 3 approaches:"
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 · 173 lines · 72 tokens per session scan A d3d153b7e168
choice-architecture is a skill published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 1,489 once invoked, about $0.0004 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 skills, from other repositories
choice-architecture
Nudge-based choice architecture for 3-option selection UI — smart default vs active choice, outcome mapping, channel factors, RECAP, operational transparency with source attribution, post-decision reinforcement, error-forgiving undo, peak-end session design, user contribution acknowledgment. Use when presenting…
pipeline
Cash Machine 10-step B2B sales pipeline with 3 presets, verifiable checkpoints per step, trajectory logging, bottleneck detection with utilization formula, lead qualification gate (BANT 6-criteria), pipeline velocity and stall detection (2x threshold), two-tier probability scoring, BBS tracking, end-of-quarter…
quest-interview
QUEST Socratic interview methodology — beginner stance, empathic neutrality, downward/upward questioning, echo questions, concept identification, permission checks, critical point pursuit, anti-pattern safeguards, resolution imbalance diagnostic, workaround discovery, painkiller vs vitamin test, locally famous test.…
review-engine
5-question review framework (result, execution, plan, strategy, analysis), KPI propagation monitoring with 4-layer anomaly patterns, One-Way/Two-Way Door classification, withdrawal decision protocol, and assumption provenance auditing. Use during periodic reviews, buffer zone changes, or when evaluating why results…
anticipatory-selling
Auto-generate 5 sales support materials for pipeline Steps 5-7 — competitive comparison table, 3-year TCO analysis, internal proposal template, objection rebuttals, phased implementation timeline. Core principle is arming the buyer to sell internally. Use when deals reach Step 5+ or when win rates at Steps 5-7 are low.
confidence
Contextual confidence calibration — DEFLATE for One-Way Doors and RED zones, PROTECT for Two-Way Doors and fundraising, "How does this work step by step?" depth testing, values-to-consequences redirect, unanimity as risk signal. From Knowledge Illusion — overconfidence is sometimes functional. Use when calibrating…