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 commands/voxtechnologies/anty-framework/scangit clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWhat 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 | $0.00013 | $0.01773 |
| Opus 5 | $0.00006 | $0.00886 |
| Sonnet 5 | $0.00003 | $0.00355 |
| Haiku 4.5 | $0.00001 | $0.00177 |
Grade A, and why
scan 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 yesterday.
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:
- scan — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anty:scan — Analysis Cycle (10-Point)
Trigger
User runs /anty:scan
Behavior
Execute a comprehensive 10-point analysis using the Analyst subagent. Read all .anty/ state files, perform each check, save results, and propose recovery actions if issues are found.
Agent
Use the Analyst subagent (agents/analyst.md) to perform all analysis checks.
10-Point Analysis
1. Buffer Consumption vs Progress
- Read goal from
.anty/goals/*.yaml - Calculate:
buffer_consumed_pct = (elapsed_time - planned_time_for_current_progress) / total_buffer - Compare buffer consumption rate against progress rate
- Flag if buffer consumption outpaces progress (RED zone)
- Assessment: GREEN / YELLOW / RED with explanation
2. KPI Propagation Check
- Read drivers from
.anty/drivers/*.yamland actions from.anty/actions/*.yaml - Trace: Action execution -> Driver metric movement -> Goal progress
- Identify broken propagation chains (actions executed but driver metric unchanged)
- Identify phantom metrics (driver moving without corresponding actions)
- Assessment: propagating / partially blocked / blocked
3. Pipeline Stall Detection
- Read deals from
.anty/pipeline/deals/*.yaml - Calculate average dwell time per step
- Flag deals exceeding 2x average dwell time for their current step
- List stalled deals with step name, dwell days, and average
- Assessment: flowing / stalls detected / critical stalls
4. Driver Impact Weight Recalculation
- Analyze metric movement data for each driver
- Recalculate impact_weight based on observed correlation between driver metric changes and goal progress
- Compare new weights with current weights
- Propose weight adjustments if delta > 5%
- Assessment: weights accurate / adjustment recommended
5. Failure Pattern Detection
- Read
.anty/scratchpad.mdand.anty/learning/choice-history.yaml - Detect 3+ consecutive failures on the same approach or driver
- Identify repeating failure patterns
- Reference
.anty/learning/failure-patterns.yamlfor known patterns - Assessment: no patterns / pattern detected (with description)
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.
- yesterday First seen · 207 lines · 13 tokens per session scan A 29e358c0f78d
scan is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,773 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
onboard
/anty:onboard — QUEST-Based Conversational Interview.
plan
/anty:plan — Strategy Kernel Generation.
actions
/anty:actions — 3-Option Choice Approval with Nudge Architecture.
review
/anty:review — 5-Question Review Engine.
scan
/anty:scan — Analysis Cycle (10-Point).
quickstart
/anty:quickstart — 5-Minute Quick Onboarding to First Action.