full-check

A comprehensive health check for the agent's commands, memory files, links, and project Git repositories. Git is a tool that tracks changes to files.

In plain words
What is it for?
Use it for a weekly review, after major changes, or when checking commands, memory, Git status, or a specific project.
Why use it?
It helps find outdated paths, duplicate notes, missing links, oversized files, and repository problems in one audit.

Command

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 commands/helloruru/claude-memory-engine/full-check
Clone the repo
git clone --depth 1 https://github.com/HelloRuru/claude-memory-engine
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 755 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00000 $0.00755
Opus 5 $0.00000 $0.00378
Sonnet 5 $0.00000 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 2d ago against content hash 268fd52af40f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

full-check scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

- `~/.claude/settings.json` -- hooks configuration present?
commands/full-check.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/full-check -- Comprehensive Health Check

Run a thorough scan of the entire memory ecosystem. Recommended weekly or after major changes.

Usage

  • /full-check -- Full audit of everything (default)
  • /full-check commands -- Deep audit of command layer only
  • /full-check memory -- Deep audit of memory files only
  • /full-check git -- Only check git repo status across all projects
  • /full-check {project} -- Full audit scoped to a specific project

Includes everything from /check (quick health check) plus the following:

Additional Checks

7. Command Layer

  • List all commands, map each to its function
  • Detect overlapping commands (similar function, different name)
  • Verify all file paths referenced in commands still exist
  • Flag outdated commands referencing deleted files

8. Memory File Audit

  • Every memory file: is it indexed in MEMORY.md? (find orphans)
  • Every MEMORY.md entry: does the target file exist? (find broken links)
  • Cross-file duplicate content detection
  • Line counts for all files (flag files over 300 lines)
  • Verify internal path references are still valid

9. Cross-Reference Integrity

  • Full chain: MEMORY.md -> memory/*.md -> skills -> references/
  • Check for rules duplicated between CLAUDE.md and MEMORY.md (should live in only one place)
  • Check for conflicting trigger phrases across commands and skills

10. Environment Config

  • ~/.claude/settings.json -- hooks configuration present?
  • ~/.claude/scripts/hooks/ -- all hook scripts exist and readable?
  • ~/.claude/sessions/ -- session directory exists?
  • ~/.claude/skills/learned/ -- skills directory exists?

11. Git Repository Status

  • Scan known repositories (from project config)
  • Each repo: uncommitted changes? Behind remote?
  • Flag repos with dirty working trees

Output Format

=== Full Health Check ===

--- Basic (same as /check) ---
{Quick health check output}

--- Commands ---
- commands/: {N} commands
- [OK] diary.md -- reflection diary
- [WARNING] {file} -- overlaps with {other file}
- [BROKEN] {file} -- references non-existent path

--- Memory Files ---
- memory/: {N} files, {total} lines
- [OK] {file} ({N} lines) -- indexed in MEMORY.md
- [ORPHAN] {file} -- not in MEMORY.md index
- [FAT] {file} has {N} lines, suggest splitting

--- Cross-References ---
- [OK] MEMORY.md -> memory/ -> skills -> references/ chain intact
- [DUPLICATE] "{rule}" appears in both CLAUDE.md and MEMORY.md
- [CONFLICT] trigger "{phrase}" used by both {cmd A} and {skill B}

--- Environment ---
- settings.json: OK (hooks configured)
- hooks/: {N} scripts
- sessions/: OK
- skills/: OK

--- Git Repos ---
- [CLEAN] {repo} -- synced with remote
- [DIRTY] {repo} -- {N} uncommitted files
- [BEHIND] {repo} -- {N} commits behind remote

Suggestions:
1. ...
2. ...

Read the full file on GitHub · 92 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 · 92 lines · 0 tokens per session scan B 268fd52af40f

Subscribe to this mod's changes

full-check is a command published in the GitHub repository HelloRuru/claude-memory-engine (133 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 755 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.