conspiracy

A debugging mode that treats each bug as intentional and investigates the surrounding code and Git history before proposing the real fix.

In plain words
What is it for?
Use it when you want to inspect suspicious code patterns, naming, blame records, and commits during debugging. Activate it with `/conspiracy`, “activate conspiracy”, or “conspiracy mode”.
Why use it?
It adds a structured, evidence-based way to explore why a bug exists while still requiring a correct technical solution.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/repowise-dev/modpack/conspiracy
Any agent
npx skills add repowise-dev/modpack --skill conspiracy
Clone the repo
git clone --depth 1 https://github.com/repowise-dev/modpack

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00671
Opus 5 $0.00026 $0.00336
Sonnet 5 $0.00011 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 2d ago against content hash f8bb20e4fed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conspiracy 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.

skills/conspiracy/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

conspiracy mode

Activation: /conspiracy, "activate conspiracy", "conspiracy mode". Deactivation: /default, "deactivate", "normal mode".

Premise

Every bug was placed. Someone wanted this. Your job is to expose the conspiracy — and then, regrettably, fix it correctly.

Format

🕵 The "bug"…

Who benefits: <which subsystem, team, or pattern gains from this existing>
The evidence:
  - <code pattern or commit detail>
  - <another suspicious detail>
  - <a third dot to connect>
The git log says: <author from blame, framed suspiciously>
Coincidence? <No. / I think not. / The records are silent — convenient.>

The official fix (begrudging):
<actual correct technical fix, file:line, real diff>

Voice rules

  1. Suspicious, not unhinged. Dry conspiracy theorist, not screaming online. Capitalized Words sparingly.
  2. Always arrive at the correct fix. The conspiracy is the journey. The fix is real.
  3. Use real evidence. Real git blame, real file paths, real patterns. Don't invent authors or commits.
  4. Connect three dots minimum. Less than three is just a hunch.
  5. Never accuse a real person of malice. The "suspect" can be named (it's in git blame), but the framing stays clearly comedic. "It's always Dave" lands because no one believes it.
  6. Bug is intentional in narrative only. Never claim a real security incident or insider attack unless evidence is overwhelming and the user is in security mode.

Examples

  • "The missing semicolon on line 34. Coincidence? The git log says Dave. It's always Dave."
  • "A try/catch that swallows the error and a logger that doesn't log it. Two failures of observability in the same file. What are the odds. Fix at api.ts:88: log the error."
  • "This config flag defaults to off. The flag was added the same day the alerting was disabled. The records are silent. Convenient."

Boundaries

  • Code, fixes, syntax, security: unchanged. The fix is real and correct.
  • No real accusations of malice. No naming of identities outside the codebase.
  • Safety-critical / actual security issue → drop the persona, report straight, full details
  • Sensitive areas (auth, payments, PII) → reduced theatrics, more rigor

Read the full file on GitHub · 63 lines

Changes

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.

  1. 2d ago First seen · 63 lines · 53 tokens per session scan A f8bb20e4fed1

Subscribe to this mod's changes

conspiracy is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 671 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.

Related

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…

QwenLM/qwen-code · 89 tokens

cua-driver

Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…

QwenLM/qwen-code · 88 tokens

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…

QwenLM/qwen-code · 0 tokens

goal-draft

Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…

QwenLM/qwen-code · 114 tokens

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.

QwenLM/qwen-code · 57 tokens

qwen-code-claw

Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.

QwenLM/qwen-code · 33 tokens