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 skills/voxtechnologies/anty-framework/kpi-treenpx skills add VoxTechnologies/anty-framework --skill kpi-treegit 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/kpi-tree)<a href="https://agentmods.dev/skills/voxtechnologies/anty-framework/kpi-tree"><img src="https://agentmods.dev/badge/skills/voxtechnologies/anty-framework/kpi-tree.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 | $0.00062 | $0.01306 |
| Opus 5 | $0.00031 | $0.00653 |
| Sonnet 5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
kpi-tree 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 4d 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:
- kpi-tree — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KPI Tree Decomposition
When to Apply
- Decomposing a new Goal into Drivers
- Re-evaluating Driver priorities after metric updates
- Identifying the constraint (Crux) Driver
- When the founder asks "where should we focus?"
- Periodic impact_weight recalculation
Core Framework
Goal -> Driver Decomposition
Decompose the Goal metric into its constituent factors using a formula:
Goal: 100 paying customers
Formula: customers = visitors x CVR x trial_to_paid_rate
KPI Tree:
visitors (1,200 -> 10,000)
organic_search (400 -> 5,000) -> Driver: SEO content
social (300 -> 2,000) -> Driver: Social growth
referral (200 -> 1,500) -> Driver: Referral program
direct (300 -> 1,500) -> Driver: PR & media
CVR (1.5% -> 3.0%)
lp_optimization -> Driver: Landing page A/B
cta_improvement -> Driver: CTA copy
trial_to_paid (20% -> 40%)
onboarding -> Driver: Tutorial improvement
follow_up -> Driver: Nurture email design
Each Driver inherits a sub-metric from the KPI tree.
Impact_weight Assignment
Initial assignment based on estimated effort-to-impact ratio. Updated dynamically as measured results come in:
Initial (agent estimate): After 2 weeks (measured):
SEO content: 0.30 SEO content: 0.15 (down - no traffic change)
Social growth: 0.25 Social growth: 0.35 (up - viral post)
Referral: 0.20 Referral: 0.25 (up - high CVR)
LP A/B: 0.15 LP A/B: 0.15 (pending)
Nurture: 0.10 Nurture: 0.10 (not started)
Update rules:
- Actions completed but no metric movement -> weight reduced
- Metric improvement detected -> weight increased
- Highest weight = current bottleneck = constraint Driver
Crux Identification (Importance x Tractability)
Every Driver evaluated on two axes:
Tractability ->
Low High
Importance +---------------+---------------+
| | | |
High | AVOID | CRUX | <- All effort here
| (important | (important |
| but can't | AND solvable)|
| solve now) | |
+---------------+---------------+
Low | IGNORE | NICE TO HAVE |
| | (do later) |
+---------------+---------------+
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.
- 4d ago First seen · 136 lines · 62 tokens per session scan A 8fa0e2e37cbc
kpi-tree is a skill published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,306 once invoked, about $0.0003 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…
culture-map
Erin Meyer's Culture Map with 8 dimensions, 5 launch presets (US, JP, DE, UK, FR), Layer A agent-user adaptation, Layer B content-target market adaptation, and anti-sycophancy tone calibration per culture. Use when adapting communication style to the founder's culture, localizing content for target markets, or when…
failure-essence
4 strategic failure patterns from Essence of Failure — dual-objective trap (conflict stress test), strategic ambiguity (operationalizability test), withdrawal decision protocol (pre-committed stop conditions, re-present biweekly), assumption provenance auditing (source, verification, load-bearing flag, sample size).…
kpi-tree
KPI tree decomposition from Goal to Drivers, formula-based factorization, impactweight assignment and dynamic update, Crux identification via importance x tractability, constraint Driver identification, input vs output metric classification. Use when decomposing Goals, prioritizing Drivers, or re-evaluating impact…
network-effects
Andrew Chen's Cold Start Problem framework — atomic network definition with thresholds by product type, anti-peanut-buttering, zero tracking, escape velocity 3-force decomposition (engagement/acquisition/economic), growth ceiling 5-force detection, competitive position dynamics, T2D3 benchmark. Use for products with…
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…