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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/baryon-mode)<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/baryon-mode"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/baryon-mode/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/commands/ancplua/ancplua-claude-plugins/baryon-mode"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/baryon-mode.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.02706 |
| Opus 5.5 | $0.00020 | $0.01082 |
| Sonnet 5.5 | $0.00010 | $0.00541 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
baryon-mode 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 14d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BARYON MODE — One-Shot Warning Exterminator
Noble Phantasm. Triggers at battle start. 8 aspects manifest. Phantasm concludes.
Solution: $0 (path to .sln or directory) Scope: $1 (default: all | nullability|deprecation|unused|async|style|suppressions|packages|config)
ARCHITECTURE
INVOKER (You — Phase 0: snapshot + categorize)
│
├─ T₀ BURST: up to 9 agents — ALL IN ONE MESSAGE
│ │
│ ├── recon-invoker ← True Name disclosure (Rider MCP + NuGet MCP)
│ │
│ ├── aspect-nullability ← CS8600-CS8799
│ ├── aspect-deprecation ← CS0612, CS0618, SYSLIB*, CA1422
│ ├── aspect-unused ← CS0168, CS0219, IDE0051-IDE0060
│ ├── aspect-async ← CS4014, CS1998, CA2007, CA2008, CA2016
│ ├── aspect-style ← IDE0001-IDE0100, SA1*, RCS*
│ ├── aspect-suppressions ← #pragma, SuppressMessage, NoWarn
│ ├── aspect-packages ← NU*, CPM, version conflicts
│ └── aspect-config ← .editorconfig, Directory.Build.props, analyzers
│
└─ PHANTASM CONCLUDES: dotnet build → delta → exit
<CRITICAL_EXECUTION_REQUIREMENT>
STEP -1 — Inherit Prior Findings:
If <EXODIA_FINDINGS_CONTEXT> tag exists in session context, read .eight-gates/artifacts/findings.json.
Filter findings with category == "SUPP" (suppression findings). Inject as known-issues for the Invoker's
categorization step — skip re-discovering suppressions already catalogued.
THIS IS A NOBLE PHANTASM. ONE BURST. NO GATES. NO PERMISSION.
- Phase 0: Run
dotnet build, capture ALL warnings, categorize into 8 buckets - IF
$1!=all: filter buckets to only the requested scope - T₀: Launch recon-invoker + ALL aspects that have warnings in scope — ONE message
- Phantasm Concludes:
dotnet buildagain, report delta, exit
NO asking "should I continue?" EVER. NO gates between burst and verification. RECKLESS MODE: Fix everything. Verify once. Exit. Only launch aspects that have warnings in their category. Skip empty buckets. IF $1 specifies a scope: only launch that aspect. Ignore all other buckets.
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.
- 14d ago First seen · 279 lines · 51 tokens per session scan A 481cf8dfc23a
baryon-mode is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 2,706 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other commands, from other repositories
test
Run .NET TDD workflow — write failing xUnit/MSTest tests, implement, verify. For bugs, use the Prove-It pattern.
scripts
Commands for creating C# script files, attaching MonoBehaviours to GameObjects, and reading/writing serialized fields. Writing a .cs file does not make its type available — Unity must import and compile it (a domain reload) first. The flow is: createscript → recompile → poll recompilestatus (until completed/uptodate)…
lint:explain
(Ruff) Explain a ruff error and show the PROPER solution (without noqa!).
savant-node
Node.js performance optimization with Node.js Developer agent.
gradle-build
Fix Gradle build errors for Android and KMP projects.
csharp-exercise-clear
A command that prepares a .NET project with starter files for the current exercise.