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 glebis/claude-skills --skill ecosystemgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/ecosystem)<a href="https://agentmods.dev/skills/glebis/claude-skills/ecosystem"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/ecosystem/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/glebis/claude-skills/ecosystem"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/ecosystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.02664 |
| Opus 5 | $0.00053 | $0.01332 |
| Sonnet 5 | $0.00021 | $0.00533 |
| Haiku 4.5 | $0.00011 | $0.00266 |
Grade A, and why
ecosystem scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
MINI_OUTPUT=$(ssh -T -o ConnectTimeout=5 -o BatchMode=yes mac-mini 'export TERM=dumb; thumb=$(curl -s --max-time 3 -o /dev/null -w "%{http_code}" http://localhost:8080/ 2>/dev/null); viz=$(curl -s --max-time 3 -o /dev/nu How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecosystem Audit
On-demand audit of the Claude Code ecosystem. Runs 4 checks, prints a full report with an attention summary, and appends a summary to today's daily note.
Workflow
Run all 4 checks sequentially using the bash blocks below. Each block runs in a fresh shell, so after all checks complete, compose the daily note summary and attention rollup from the terminal output you've collected.
CRITICAL: Run date +"%Y%m%d" before writing to the daily note.
Step 1: Skill Health
Scan ~/.claude/skills/ for skill freshness and broken symlinks.
NOW=$(date +%s)
D30=$((NOW - 30*86400))
D90=$((NOW - 90*86400))
ACTIVE="" BROKEN=""
ACTIVE_N=0 RECENT_N=0 STALE_N=0 BROKEN_N=0 TOTAL=0
for entry in ~/.claude/skills/*/; do
[ -d "$entry" ] || continue
name=$(basename "$entry")
TOTAL=$((TOTAL + 1))
if [ -L "${entry%/}" ] && [ ! -e "${entry%/}" ]; then
target=$(readlink "${entry%/}")
BROKEN="${BROKEN} - ${name} -> ${target}\n"
BROKEN_N=$((BROKEN_N + 1))
continue
fi
real_path="$entry"
if [ -L "${entry%/}" ]; then
real_path="$(readlink "${entry%/}")/"
fi
newest=$(find "$real_path" -type f -exec stat -f %m {} + 2>/dev/null | sort -rn | head -1)
[ -z "$newest" ] && newest=0
if [ "$newest" -ge "$D30" ]; then
ACTIVE="${ACTIVE}, ${name}"
ACTIVE_N=$((ACTIVE_N + 1))
elif [ "$newest" -ge "$D90" ]; then
RECENT_N=$((RECENT_N + 1))
else
STALE_N=$((STALE_N + 1))
fi
done
echo "### Skills (${TOTAL} total)"
echo "- Active (30d): ${ACTIVE_N}${ACTIVE:+ — ${ACTIVE:2}}"
echo "- Recent (30-90d): ${RECENT_N}"
echo "- Stale (>90d): ${STALE_N}"
echo "- Broken symlinks: ${BROKEN_N}"
[ -n "$BROKEN" ] && printf "$BROKEN"
Step 2: Project Pulse
Scan ~/ai_projects/ for git repo activity and CLAUDE.md presence. Cap dormant and abandoned lists at 10 names to keep output readable.
NOW=$(date +%s)
D30=$((NOW - 30*86400))
D180=$((NOW - 180*86400))
ACTIVE="" DORMANT="" ABANDONED="" DORMANT_N=0 ABANDONED_N=0 NO_CLAUDE=0
ACTIVE_N=0 GIT_TOTAL=0 DIR_TOTAL=0 NODATA=0
for dir in ~/ai_projects/*/; do
[ -d "$dir" ] || continue
DIR_TOTAL=$((DIR_TOTAL + 1))
[ -d "${dir}.git" ] || continue
GIT_TOTAL=$((GIT_TOTAL + 1))
last_commit=$(git -C "$dir" log -1 --format=%ct 2>/dev/null)
if [ -z "$last_commit" ]; then
NODATA=$((NODATA + 1))
continue
fi
name=$(basename "$dir")
if [ "$last_commit" -ge "$D30" ]; then
ACTIVE="${ACTIVE}, ${name}"
ACTIVE_N=$((ACTIVE_N + 1))
elif [ "$last_commit" -ge "$D180" ]; then
DORMANT_N=$((DORMANT_N + 1))
[ "$DORMANT_N" -le 10 ] && DORMANT="${DORMANT}, ${name}"
else
ABANDONED_N=$((ABANDONED_N + 1))
[ "$ABANDONED_N" -le 10 ] && ABANDONED="${ABANDONED}, ${name}"
fi
[ ! -f "${dir}CLAUDE.md" ] && NO_CLAUDE=$((NO_CLAUDE + 1))
done
DORMANT_SUFFIX=""
[ "$DORMANT_N" -gt 10 ] && DORMANT_SUFFIX=" and $((DORMANT_N - 10)) more"
ABANDONED_SUFFIX=""
[ "$ABANDONED_N" -gt 10 ] && ABANDONED_SUFFIX=" and $((ABANDONED_N - 10)) more"
echo ""
echo "### Projects (${DIR_TOTAL} dirs, ${GIT_TOTAL} git repos)"
echo "- Active (30d): ${ACTIVE_N}${ACTIVE:+ — ${ACTIVE:2}}"
echo "- Dormant (30-180d): ${DORMANT_N}${DORMANT:+ — ${DORMANT:2}${DORMANT_SUFFIX}}"
echo "- Abandoned (>6mo): ${ABANDONED_N}${ABANDONED:+ — ${ABANDONED:2}${ABANDONED_SUFFIX}}"
[ "$NODATA" -gt 0 ] && echo "- No data (empty/corrupt): ${NODATA}"
echo "- Missing CLAUDE.md: ${NO_CLAUDE}"
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.
- 10d ago First seen · 228 lines · 106 tokens per session scan A 8bf045d20530
ecosystem is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 7d ago), licensed MIT. It adds 106 tokens to every session and 2,664 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…