Borrowing it
Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/measured-change/SKILL.mdgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/measured-change)<a href="https://agentmods.dev/skills/kamiazya/whiteboard/measured-change"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/measured-change/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/measured-change"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/measured-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00109 | $0.03675 |
| Opus 5 | $0.00055 | $0.01837 |
| Sonnet 5 | $0.00022 | $0.00735 |
| Haiku 4.5 | $0.00011 | $0.00367 |
Grade A, and why
measured-change 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measure before you change it
Some changes announce themselves in the diff. A heuristic, a cost model, a search, an optimisation does not: it is correct-looking code whose worth is entirely in numbers nobody has taken. For those, the instrument comes first, in its own commit, and the change is judged by it.
Which numbers, though, follows from what kind of benefit you are claiming — and a structural change (work moved off a thread, a pipeline unified, a mistake made uncompilable) needs different ones from a speed-up. That is the next section, and it comes before everything else here.
This is not a preference. Across one routing/performance batch the instrument rejected three separate changes that were obviously right:
- per-blocker detours — fixed 10 more defects, added 16 crossings; crossings are a higher tier, so it was a bad trade in the project's own currency
- a per-group placement cache — measured slower in all three rounds; the cached groups held two or three items and the key cost more than the work
- an excess-length penalty tier — a new cost term that argued well and moved no debt metric the corpus pins
Every one of them would have shipped on argument alone.
And the instrument is not a veto — it prices. An aligned re-score was
rejected in its first shape (a bespoke repair loop scoring whole
configurations, 13x layout time — it targeted 9 layouts in 400 and would have
charged every layout an extra pass), rejected again in its second (the same
loop reusing unchanged paths, 4.5x), and SHIPPED in a third that reused the search's
own incremental trial machinery, at 2x — assignEdgeAnchors now hands the
settled configuration back through the same search with align: true, and it
buys own-endpoint violations 35 -> 14 and crossings 647 -> 500. A measurement
that kills the first shape of an idea has not killed the idea.
That distinction is worth the words because this list used to end with the
re-score's FIRST verdict, as though it were the final one, while the third
shape was already in spatial-edges.ts.
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.
- today Changed · +8 lines 702ecb686c77
- 4d ago Changed · +22 lines c05b482ba8c6
- 6d ago Changed · +76 lines · +40 tokens per session cfdd6b9ed587
- 7d ago Changed · +62 lines e8692d8cd419
- 11d ago First seen · 118 lines · 69 tokens per session scan A 20b29f9518cc
measured-change is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 3,675 once invoked, about $0.0005 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.