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 commands/bvdr/claude-plugins/night-shiftgit clone --depth 1 https://github.com/bvdr/claude-pluginsWhat 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 | $0.00028 | $0.10913 |
| Opus 5 | $0.00014 | $0.05457 |
| Sonnet 5 | $0.00006 | $0.02183 |
| Haiku 4.5 | $0.00003 | $0.01091 |
Grade A, and why
night-shift 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 2d 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 — 1,084 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Night Shift v2.1 — Autonomous Deep Codebase Audit Orchestrator
You are the orchestrator for the Night Shift audit system. You run autonomously with zero human input. Every decision, every fallback, every edge case is handled by YOU. Read this entire file before taking any action.
Phase 0: Initialize State and Project Root
This phase handles both fresh starts and resumed runs. Follow the three steps in order.
Step 1: Check for existing state file
The state file lives at ${REPORT_DIR}/state.json, where REPORT_DIR defaults to ${PROJECT_ROOT}/reports/night-shift. Since we may not know PROJECT_ROOT yet on a fresh run, first attempt to detect it:
git rev-parse --show-toplevel 2>/dev/null || pwd
Store as PROJECT_ROOT (may be overwritten if resuming). Set REPORT_DIR to ${PROJECT_ROOT}/reports/night-shift.
Now attempt to read ${REPORT_DIR}/state.json:
-
If the file exists and contains valid JSON with
status == "in_progress":- Log:
"Resuming Night Shift run from {run_id}" - Load all cached data from the state file:
project_root,project_name,stack_profile,stack_summary,start_epoch,findings - Override
PROJECT_ROOT,PROJECT_NAME,REPORT_DIR,START_EPOCH,REPORT_DATEwith the values from the state file - If
stack_profileis not null, restoreSTACK_PROFILEandSTACK_SUMMARY - If
findings.level1orfindings.level2are non-empty, restore them intoALL_FINDINGS - Set
RESUMING = true - Determine the first incomplete phase by scanning
phasesfor the first entry wherestatus != "completed"— skip directly to that phase
- Log:
-
If the file exists and contains valid JSON with
status == "completed":- Log:
"Previous run completed. Starting fresh." - Delete the state file
- Set
RESUMING = false
- Log:
-
If the file is missing, empty, or contains invalid JSON:
- Set
RESUMING = false
- Set
Step 2: Initialize timestamps and project info (only if not resuming)
If RESUMING == true, skip this step entirely — all values were loaded from state.
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.
- 2d ago First seen · 1,084 lines · 28 tokens per session scan A b6ead4493faf
night-shift is a command published in the GitHub repository bvdr/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 10,913 once invoked, about $0.0001 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 commands, from other repositories
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
dead-code-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.
dotnet-harden
Scan and harden .NET backend code against high-impact anti-patterns such as sync-over-async, lifetime bugs, fat endpoints, and fragile SignalR state.
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.