ai-agents-diagnostics-toolkitlisted

# ai-agents Diagnostics Toolkit <!-- vendor-portability: contributor-facing knowledge pack for the rjmurillo/ai-agents repo itself; intentionally references upstream paths (.agents/, .claude/, scripts/, build/) because its audience is repo contributors, not plugin consumers (issue #2050) --> Measure instead of eyeball. Every instrument below is a read-only command that turns a vague worry ("are skills getting bloated?", "did generation drift?") into a number you can compare against a baseline. This file gives you, per instrument: the question it answers, the exact command, the healthy and unhealthy reading, the current repo baseline (as of 2026-07-02), and the trap that has already cost someone time. Vocabulary, defined once: an "instrument" is a script whose output you read, not a gate you must pass. A "drift gate" is a CI check that fails when a generated tree stops matching its canonical source. "EVENT telemetry" is the one-line JSON a push guard prints to stderr when it runs. A "baseline" is the number the instrument reports on a clean checkout of main; you measure your delta against it. ## Triggers - `measure this` - `read the drift signal` - `check skill budgets` - `guard maturity report` - `interpret this scan output` ## Instrument Index | Instrument | Question it answers | Command (from repo root) | |---|---|---| | Description budget | How much standing context do skill descriptions cost? | `uv run python ./scripts/skill_description_budget.py` | | Skill size | W