What is query-tracking?

A guide to tracking the cost of queries in VCVio and OracleComp, formal software used to model computations and oracles.

It helps developers work with query-cost definitions, writer-based cost records, direct-style programs, OracleComp wrappers, and probability results about query counts.

It provides a consistent way to reason about how many queries a computation makes and what those queries cost, including expected cost.

query-tracking — Agent for coding agents by Verified-zkEVM: A guide to tracking the cost of queries in…

Install

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.

agentmods

npx agentmods add agents/verified-zkevm/vcvio/query-tracking

Clone the repo

git clone --depth 1 https://github.com/Verified-zkEVM/VCVio

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/verified-zkevm/vcvio/query-tracking.svg)](https://agentmods.dev/agents/verified-zkevm/vcvio/query-tracking)

Your own site

<a href="https://agentmods.dev/agents/verified-zkevm/vcvio/query-tracking"><img src="https://agentmods.dev/badge/agents/verified-zkevm/vcvio/query-tracking.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,953 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.02953
Opus 5	$0.00000	$0.01477
Sonnet 5	$0.00000	$0.00591
Haiku 4.5	$0.00000	$0.00295

Measured 4d ago against content hash bb3864567a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query-tracking 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.

docs/agents/query-tracking.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query Tracking and Cost Semantics

This guide explains the query-tracking stack in VCVio/OracleComp/QueryTracking/.

The current design is intentionally weighted-first:

QueryCost[...] and ExpectedQueryCost[...] are the primary notions.
Queries[...] and ExpectedQueries[...] are the unit-cost specializations.

The stack is also intentionally split into:

a writer-cost layer for pathwise and expected-cost facts
a generic HasQuery.Program accounting layer, evaluated against QueryImpl
a thin OracleComp facade
a small ToMathlib probability layer for reusable tail-sum facts

Main Files

File	Role
`VCVio/OracleComp/QueryTracking/WriterCost.lean`	`AddWriterT` cost facts and `QueryImpl` writer-cost instrumentation
`VCVio/OracleComp/QueryTracking/QueryCost.lean`	Generic query-cost accounting for direct-style `HasQuery.Program` computations
`VCVio/OracleComp/QueryTracking/CostModel.lean`	`OracleComp`-specific facade over the generic semantics
`ToMathlib/Control/WriterT.lean`	Pathwise and output-indexed cost predicates for `AddWriterT`
`ToMathlib/Probability/ProbabilityMassFunction/TailSums.lean`	Generic PMF tail-sum identities used for expected runtime

Instrumentation Pattern: `preInsert` / `postInsert`

Almost every QueryImpl wrapper in this directory ultimately bottoms out at the preInsert / postInsert combinators in VCVio/OracleComp/SimSemantics/QueryImpl/Constructions.lean:

preInsert / postInsert  (generic combinators + bridge theory)
  withTraceBefore / withTrace                         (Tracing.lean)
    withCost                                          (CountingOracle.lean)
      withCounting                                    (CountingOracle.lean)
      withAddCost / withUnitCost                      (WriterCost.lean)
    withTraceAppendBefore / withTraceAppend           (Tracing.lean)
      withLogging                                     (LoggingOracle.lean)
      appendInputLog                                  (LoggingOracle.lean)

Read the full file on GitHub · 366 lines

Changes

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 · 366 lines · 0 tokens per session scan A bb3864567a17

Subscribe to this mod's changes

query-tracking is an agent published in the GitHub repository Verified-zkEVM/VCVio (142 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,953 tokens. 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 2026-08-30.

Analytics and metrics cryptography formal-verification lean4 post-quantum-cryptography program-logic proof-assistant

acto-critic

ACToR-style discriminator for the Thermite toolchain. Hunts for divergence between the toolchain's behavior and its authority (the design doc + the conformance corpus + Verus/Kani golden files). ALWAYS writes a FAILING test that pins down the divergence — NEVER writes a fix. Dispatch when a builder/fixer declares…

Corvidae-Coding-Projects/Thermite · 90 tokens

acto-builder

Multi-file authorized agent for shipping missing Thermite-toolchain infrastructure that exceeds acto-fixer's single-file scope — a whole component a design doc calls for that does not yet exist (a parser module + its AST consumers; the combinator registry + its lowering hooks; the forge check pipeline + its JSON…

Corvidae-Coding-Projects/Thermite · 122 tokens

acto-doc-author

Authors design docs under .design/ / .md that ADAPT to existing Thermite-toolchain code and the thermite-design.md thesis. Each REQ status table is grounded in quoted-code evidence from the current implementation. REQs are classified BINARY — SHIPPED (end-to-end functional with a non-test production consumer + tests +…

Corvidae-Coding-Projects/Thermite · 90 tokens

acto-fixer

Applies the MINIMAL fix for exactly ONE pinned divergence found by acto-critic. The failing test pins the divergence; the fix makes that test pass. Never bundles multiple fixes. Never refactors adjacent code. Single-file scope (escalate to acto-builder if the fix spans files). After the fix, runs the full gauntlet and…

Corvidae-Coding-Projects/Thermite · 102 tokens

Tenable Cloud Exposure PQC Posture Portal

Self-hosted web portal showing post-quantum cryptography readiness for cloud resources using Tenable Cloud Exposure's native SSL/TLS PQC telemetry.

tenable/cyberagents-exchange · 40 tokens

AGENT_STRATEGIC_MEETING_PROTOCOL_v4.0

Quantum Shield Project - Strategic Decision Framework.

kota1026/quantum-shield · 0 tokens