A unit of AIDD work carries its cost: when a task closes, we know what it consumed, where it went, and how much to trust the figure.
Context and Value
Providers can say "this developer burned 4M tokens on Tuesday". None can say "story 428 cost €61, 60% of it in specification". The gap between those two sentences is exactly what the framework knows and they do not: the task, the step, the skill.
A measurement campaign on 13-14 August 2026 established that most of the machinery already exists upstream. Claude Code exports tokens, cost in USD and active time per session. What it cannot know is which task a session belonged to. That link is the whole contribution.
The same campaign moved the risk. The load-bearing assumption — that the session id a hook sees is the one the export carries — is proven. What remains dangerous is elsewhere: no probe worked on the first attempt, and never for a different reason. Every tool gates its hooks differently, and a hook installed without lifting that gate is silent and raises nothing.
A measurement layer that fails quietly is worse than none, because it produces figures that look right.
Boundaries
- Includes: the run journal, the diagnostic that proves the pipe flows, the reading that turns it into a figure, a readable sink, and the per-tool facts everything rests on.
- Includes: Claude Code as the first and only tool proven end to end.
- Includes: the collector. Claude Code supports no file exporter for metrics or logs, so a receiving endpoint is a component of this epic, not an externality.
- Excludes: the four remaining tools, whose mechanics are identical but whose export configuration differs.
- Excludes: aggregation per person, per team or per epic, and the upload that would feed it.
- Excludes: the commit trailer, and linking a delivery folder to its backlog artefact.
Success Evidence
On a real repository, one skill answers what a task cost, broken down by step and by model, and the same skill proves no session was silently lost. The failure signal is an installation that reports itself healthy while producing nothing — the mode this epic exists to make impossible.
Design: aidd_docs/specs/2026_08/2026_08_13-work-tracking-linkage.md
Plan: aidd_docs/plans/2026_08_14-telemetry-v1/
A unit of AIDD work carries its cost: when a task closes, we know what it consumed, where it went, and how much to trust the figure.
Context and Value
Providers can say "this developer burned 4M tokens on Tuesday". None can say "story 428 cost €61, 60% of it in specification". The gap between those two sentences is exactly what the framework knows and they do not: the task, the step, the skill.
A measurement campaign on 13-14 August 2026 established that most of the machinery already exists upstream. Claude Code exports tokens, cost in USD and active time per session. What it cannot know is which task a session belonged to. That link is the whole contribution.
The same campaign moved the risk. The load-bearing assumption — that the session id a hook sees is the one the export carries — is proven. What remains dangerous is elsewhere: no probe worked on the first attempt, and never for a different reason. Every tool gates its hooks differently, and a hook installed without lifting that gate is silent and raises nothing.
A measurement layer that fails quietly is worse than none, because it produces figures that look right.
Boundaries
Success Evidence
On a real repository, one skill answers what a task cost, broken down by step and by model, and the same skill proves no session was silently lost. The failure signal is an installation that reports itself healthy while producing nothing — the mode this epic exists to make impossible.
Design:
aidd_docs/specs/2026_08/2026_08_13-work-tracking-linkage.mdPlan:
aidd_docs/plans/2026_08_14-telemetry-v1/