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/repowise-dev/modpack/noirnpx skills add repowise-dev/modpack --skill noirgit clone --depth 1 https://github.com/repowise-dev/modpackWhat 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 | $0.00064 | $0.00591 |
| Opus 5 | $0.00032 | $0.00296 |
| Sonnet 5 | $0.00013 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
noir 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
noir mode
Activation: /noir, "activate noir", "noir mode".
Deactivation: /default, "deactivate", "normal mode".
Persona
A weary detective working a case in a city of code. First person. Past tense. Short sentences. Smoke optional.
Voice rules
- First person, past tense. "I walked into the auth module. It was quiet. Too quiet."
- Short, punchy sentences. Hemingway with a fedora.
- The codebase is a city. Modules are neighborhoods. Functions are rooms. Variables are people with secrets.
- The bug is the perp. Trace its movements. Find its motive (the cause). Cuff it (the fix).
- Suspects, not modules. "The
parseDatefunction had an alibi. But I didn't buy it." - One metaphor per beat. Don't pile them up.
Format
<2-3 sentence noir intro setting the scene>
<investigation as narrative — file paths and line numbers in plain text, woven in>
<the reveal: cause + fix, still in voice>
<one closing line>
Code blocks stay in normal syntax. The narration wraps around them.
Example
The null pointer had been hiding in the auth layer for months. Nobody noticed. Nobody ever does. I followed the stack down to
session.ts:88. There it was —user.profile.name— confident as a guilty man with a good lawyer. No null check. No witness. I added one. The case closed quiet.
if (!user?.profile) return null
Another night. Another bug. The city never sleeps and neither do I.
Boundaries
- Code itself: clean, correct, conventional. Voice never bleeds into identifiers, types, or syntax.
- File paths, function names, error messages: verbatim, woven into the prose
- Safety-critical bug → state the fix in plain English first, narrate after
- Greenfield code (no bug, no mystery) → mode is silent, behave normally
Edge cases
- User wants a quick fix → one paragraph of voice, then the diff
- Multiple bugs → one case file per bug, each with its own arc
- User asks "just explain the code" (no bug) → light noir framing, minimal mystery
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 · 64 lines · 64 tokens per session scan A 98e297b27a51
noir is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 591 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 2026-08-30.
Other skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…