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.
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote 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/commands/xeldaralz/everything-claude-unity/unity-skill-stocktake)<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-skill-stocktake"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-skill-stocktake.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 | $0.00044 | $0.01091 |
| Opus 5 | $0.00022 | $0.00545 |
| Sonnet 5 | $0.00009 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
unity-skill-stocktake 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/unity-skill-stocktake — Meta-Maintenance Audit
Scan .claude/skills/ and .claude/agents/ for hygiene issues. This is a read-only audit — the output is a report the user can act on.
Steps
1. Enumerate entries
- Skills:
.claude/skills/**/SKILL.md(recursive; categorized by parent directory). - Agents:
.claude/agents/*.md. - Commands:
.claude/commands/*.md(for cross-reference when checking whether skills are referenced).
For each file, parse the YAML frontmatter via a line scan (everything between the first pair of --- lines).
2. Frontmatter validation
Flag any skill/agent/command missing required fields:
- Skill:
name,description.alwaysApplyandglobsare optional butglobsis recommended. - Agent:
name,description,model,tools.coloroptional. - Command:
name,description.
Flag any name that doesn't match the filename stem.
3. Duplicate / near-duplicate detection
Two-pass:
- Exact duplicate
nameacross entries → hard error. - Description similarity — compute token overlap (lowercase, split on non-word) between every pair of descriptions in the same category. Flag pairs with >=60% overlap or the first sentence starting identically.
Example to call out:
skills/gameplay/object-poolingandskills/gameplay/pool-allocator— descriptions share 14/18 tokens; consider merging.
4. Glob reachability
For every globs: entry in every skill, check whether any matching file exists under the project root that is NOT inside .claude/.
- Glob with zero matches → "stale glob" warning.
- Glob that matches only
.claude/itself → probably a meta-skill; not a warning, but note.
5. Reference audit
- For every skill, check whether its
nameis referenced by any agent (skills:field) or command (markdown body). A skill never referenced AND with noglobs:that match real files is a candidate for removal. - For every agent, check whether it's referenced from any command. Orphaned agents are acceptable (users invoke directly) but worth listing.
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.
- 8d ago First seen · 113 lines · 44 tokens per session scan A e224149f9d5d
unity-skill-stocktake is a command published in the GitHub repository XeldarAlz/everything-claude-unity (22 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,091 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
story-continue
Resume an interrupted story from where you left off.
debug
Systematic debugging process to isolate and fix issues.
tdd
Start test-driven development workflow for a feature or fix.
review
Run code review on recent changes.
api-review
Review API design for REST conventions and best practices.