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 skills add kopp0510/claude-dd --skill statusgit clone --depth 1 https://github.com/kopp0510/claude-ddWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kopp0510/claude-dd/status)<a href="https://agentmods.dev/skills/kopp0510/claude-dd/status"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/status/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kopp0510/claude-dd/status"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.01327 |
| Opus 5.5 | $0.00008 | $0.00531 |
| Sonnet 5.5 | $0.00004 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/self-improving-agent:status — Memory Health Dashboard
Quick overview of your project's memory state across all memory systems.
Usage
/self-improving-agent:status # Full dashboard
/self-improving-agent:status --brief # One-line summary
What It Reports
Step 1: Locate all memory files
# Auto-memory directory. Claude Code replaces EVERY non-alphanumeric character in the
# resolved absolute cwd with a single "-" (dots, spaces and CJK included).
MEMORY_DIR="$HOME/.claude/projects/$(pwd -P | sed 's/[^a-zA-Z0-9]/-/g')/memory"
# The counts below are 0 when the path is wrong, which reads exactly like "healthy".
# Verify the directory first; under LC_ALL=C sed goes per byte, so glob as a fallback:
# [ -d "$MEMORY_DIR" ] || ls -d ~/.claude/projects/*"$(basename "$PWD" | sed 's/[^a-zA-Z0-9]/-/g')"*
# Count lines in MEMORY.md
wc -l "$MEMORY_DIR/MEMORY.md" 2>/dev/null || echo "0"
# List topic files
ls "$MEMORY_DIR/"*.md 2>/dev/null | grep -v MEMORY.md
# CLAUDE.md
wc -l ./CLAUDE.md 2>/dev/null || echo "0"
wc -l ~/.claude/CLAUDE.md 2>/dev/null || echo "0"
# Rules directory
ls .claude/rules/*.md 2>/dev/null | wc -l
Step 2: Analyze capacity
| Metric | Healthy | Warning | Critical |
|---|---|---|---|
| MEMORY.md lines | < 120 | 120-180 | > 180 |
| CLAUDE.md lines | < 150 | 150-200 | > 200 |
| Topic files | 0-3 | 4-6 | > 6 |
| Stale entries | 0 | 1-3 | > 3 |
Step 3: Quick stale check
For each MEMORY.md entry that references a file path:
# Verify referenced files still exist. There are TWO kinds of reference and they resolve
# against different roots — lumping them together is how this check breaks:
#
# 1. Topic-file links, always written as markdown links with a BARE filename:
# [Some title](user_role.md). They live NEXT TO MEMORY.md, so resolve against
# $MEMORY_DIR. These are the majority (a real MEMORY.md here: 47 bare vs 1 with a slash).
# 2. Project paths, which always contain "/". Resolve against the project root (cwd).
#
# Bare filenames that are NOT link targets (CLAUDE.md, ci.yml, plugin.json mentioned in
# prose) are neither kind — the link-target pattern skips them on its own. Do not "simplify"
# this into one pass: resolving everything against cwd reports ~46 false STALE on a healthy
# memory dir, and skipping every bare name makes the topic-file check dead code.
# 1. topic files — markdown link targets with no "/", resolved next to MEMORY.md
grep -oE '\]\([^)/]+\.(ts|js|py|md|json|yaml|yml)\)' "$MEMORY_DIR/MEMORY.md" \
| sed 's/^](//; s/)$//' | sort -u | while IFS= read -r f; do
[ -f "$MEMORY_DIR/$f" ] || echo "STALE (topic): $f"
done
# 2. project paths — anything containing "/", including absolute paths, resolved from cwd
grep -oE '/?([a-zA-Z0-9_.-]+/)+[a-zA-Z0-9_.-]+\.(ts|js|py|md|json|yaml|yml)' "$MEMORY_DIR/MEMORY.md" \
| sort -u | while IFS= read -r f; do
[ -f "$f" ] || echo "STALE (path): $f"
done
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.
- 1mo ago Changed · +25 lines 1a27da359f39
- 1mo ago First seen · 105 lines · 20 tokens per session scan A 5909388fa5d0
status is a skill published in the GitHub repository kopp0510/claude-dd (12 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,327 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
impl-validator
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…