debug-rules

A diagnostic tool for finding out which instruction rules loaded in a coding session and why others did not.

In plain words
What is it for?
Use it to check the logging setup, inspect loaded rules, and investigate changes to rule conditions or file-matching settings.
Why use it?
It removes guesswork when conditional instructions appear to be ignored. It uses an audit log that records loaded instructions, but requires a logging hook to be enabled first.

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/stuartshields/claude-setup/debug-rules
Any agent
npx skills add stuartshields/claude-setup --skill debug-rules
Clone the repo
git clone --depth 1 https://github.com/stuartshields/claude-setup

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00028 $0.00968
Opus 5 $0.00014 $0.00484
Sonnet 5 $0.00006 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured yesterday against content hash 5acb227a9d6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-rules scanned grade A with 1 finding 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The hook script `~/.claude/hooks/log-instructions.sh` should already exist. To enable logging, add this to `~/.claude/settings.json` under `"hooks"`:

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/debug-rules/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: debug-rules

When to Use

Use this skill when:

  • Conditional rules don't seem to be loading
  • Claude is ignoring instructions that should be in a rule file
  • You changed rule frontmatter and want to verify it works
  • You want to see what rules loaded in a specific session

Prerequisites

This skill requires the InstructionsLoaded audit hook. The hook is not registered by default - it's an on-demand diagnostic tool you enable when needed.

Setup (one-time)

The hook script ~/.claude/hooks/log-instructions.sh should already exist. To enable logging, add this to ~/.claude/settings.json under "hooks":

"InstructionsLoaded": [
  {
    "hooks": [
      {
        "type": "command",
        "command": "~/.claude/hooks/log-instructions.sh"
      }
    ]
  }
]

Then start a new session, do some work that touches files matching your conditional rules, and run /debug-rules again.

Remove the hook from settings.json when done - it's lightweight but unnecessary for normal use.

Step 1: Verify hook is active

  1. Check ~/.claude/hooks/log-instructions.sh exists and is executable
  2. Check ~/.claude/settings.json has an InstructionsLoaded entry pointing to it
  3. Check ~/.claude/instruction-audit.log exists and is non-empty

If the hook script is missing, tell the user and stop. If the hook script exists but isn't registered in settings.json, show them the setup instructions above. If the log doesn't exist or is empty, tell the user: "No audit log found. Register the hook, start a new session, do some work, then run /debug-rules again."

Step 2: Read the audit log

Read ~/.claude/instruction-audit.log. If the user provided a timestamp, filter to entries from that session. If they said "latest" or gave no argument, use the most recent session (group by timestamp - entries within 2 seconds of each other are the same session start).

Step 3: Inventory expected rules

Read all files in ~/.claude/rules/. For each file:

  • If it has no paths: frontmatter → it should appear with reason: session_start
  • If it has paths: frontmatter → it should appear with reason: path_glob_match only when matching files are read

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 28 tokens per session scan A 5acb227a9d6d

Subscribe to this mod's changes

debug-rules is a skill published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 968 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

memory

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file.

memvid/claude-brain · 21 tokens

bearing-diagnosis

Complete bearing fault diagnostic workflow using vibration analysis and the predictive-maintenance-mcp server. Use this skill when the user says "diagnose bearing", "bearing fault", "bearing check", "detect bearing damage", "bearing vibration analysis", "inner race fault", "outer race fault", "ball defect", "cage…

LGDiMaggio/predictive-maintenance-mcp · 93 tokens

prognostics

Prognostic assessment workflow: trend analysis, degradation onset detection, and Remaining Useful Life (RUL) estimation using the predictive-maintenance-mcp server. Use this skill when the user says "trend analysis", "degradation trend", "RUL", "remaining useful life", "prognosis", "prognostics", "failure prediction"…

LGDiMaggio/predictive-maintenance-mcp · 120 tokens

signal-management

Signal loading, generation, and cache management using the predictive-maintenance-mcp server. Use this skill when the user says "load signal", "import signal", "list signals", "available signals", "generate test signal", "create test data", "synthetic signal", "clear cache", "signal info", "what signals are loaded"…

LGDiMaggio/predictive-maintenance-mcp · 91 tokens

anomaly-detection

ML-based anomaly detection and model training for vibration signals using the predictive-maintenance-mcp server. Use this skill when the user says "anomaly detection", "train model", "detect anomalies", "outlier detection", "normal vs abnormal", "machine learning", "one-class SVM", "LOF", "local outlier factor"…

LGDiMaggio/predictive-maintenance-mcp · 100 tokens

gear-diagnosis

Gear fault diagnosis workflow using vibration analysis via the predictive-maintenance-mcp server. Use this skill when the user says "gear fault", "gear diagnosis", "gear mesh", "gearbox analysis", "gear vibration", "tooth damage", "gear defect", "diagnose gear", "gear mesh frequency", "sideband analysis", or wants to…

LGDiMaggio/predictive-maintenance-mcp · 78 tokens