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 skills/vchelaru/flatredball2/skill-change-loggingnpx skills add vchelaru/FlatRedBall2 --skill skill-change-logginggit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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/vchelaru/flatredball2/skill-change-logging)<a href="https://agentmods.dev/skills/vchelaru/flatredball2/skill-change-logging"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/skill-change-logging.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00052 | $0.00920 |
| Opus 5 | $0.00026 | $0.00460 |
| Sonnet 5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
skill-change-logging 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Change Logging
Use this skill whenever a skill file changes — both the 3rd-party game-dev skills under frb-skills/ and the 1st-party engine-contributor skills under .claude/skills/. Log the canonical path (e.g. frb-skills/animation/SKILL.md, not the symlinked path).
Required Log File
- Path:
.claude/skill_change_log.jsonl - Format: one JSON object per line (JSONL)
When to Log
Always append one entry per changed skill when any of these occur:
SKILL.mdcontent edits- frontmatter
nameordescriptionupdates - new skill creation
- skill deletion
- significant skill restructure (for example, moving sections into references)
Do not skip logging because a change is "small". If behavior, routing, or guardrails changed, log it.
Required Fields Per Entry
Each JSON object must include:
id: integer UTC epoch milliseconds at write time (append-only friendly)timestamp_utc: ISO-8601 UTC timestamp at millisecond precision (YYYY-MM-DDTHH:mm:ss.fffZ)skill: skill name (folder name or frontmatter name)skill_file: repo-relative pathchange_type:create,update,delete, orrestructurelines_added: integer fromgit diff --numstatlines_removed: integer fromgit diff --numstatline_ranges_added: array of 1-based line ranges in the post-change file (e.g.["42-57","89-89"])line_ranges_removed: array of 1-based line ranges in the pre-change file (e.g.["40-52"])motivating_sample_project: sample project path that motivated the change, or"none"if not sample-drivenreason: concise but complete need statement
Logging Workflow
- Make skill edits.
- Run
git diff --numstat -- <skill-file-paths>. - Run
git diff -U0 -- <skill-file-paths>and capture hunk line ranges. - Set
idto current UTC epoch milliseconds. - Append one JSON line per changed skill to
.claude/skill_change_log.jsonl. - Keep reasons short, specific, and action-oriented.
ID Rules
- IDs are global across the file (not per skill).
- IDs must be unique; they do not need to be contiguous.
- Use UTC epoch milliseconds to avoid reading the existing log for max-id lookup.
- If two entries are created in the same millisecond, increment by
+1locally for subsequent entries in that write batch.
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 · 80 lines · 52 tokens per session scan A f7f2ca669fb4
skill-change-logging is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 920 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.