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 agentmods add skills/parkerm2/create-claude-workflow/utility-setupnpx skills add ParkerM2/create-claude-workflow --skill utility-setupgit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWhat 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 | $0.00092 | $0.02111 |
| Opus 5 | $0.00046 | $0.01056 |
| Sonnet 5 | $0.00018 | $0.00422 |
| Haiku 4.5 | $0.00009 | $0.00211 |
Grade B, and why
utility-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json`. Add these entries into the `hooks` How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utility Setup
Installs three components that make every Claude session — including spawned agent worktrees — automatically aware of available utilities:
-
SessionStart hook — injects a compact utility index at the start of every session so agents know what skills and tools exist before planning any task. Fires deterministically (not probabilistic).
-
UserPromptSubmit hook — keyword-matches each incoming message and emits a 1-line skill hint when relevant. Silent otherwise — zero noise when no match.
-
codebase-nav skill — a project-level growing library of pre-built search patterns. Common grep/find tasks become one tool call instead of five. Grows automatically as new patterns are discovered.
Instructions
Step 1: Create hooks directory
mkdir -p ~/.claude/hooks
Step 2: Write session-bootstrap.sh
Create ~/.claude/hooks/session-bootstrap.sh:
#!/bin/bash
# Injected at every session start (including agent worktrees).
# Outputs compact utility index before Claude plans any task.
CWD=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
AGENT_COUNT=$(find "$CWD/.claude/agents" -name "*.md" \
-not -name "README*" 2>/dev/null | wc -l | tr -d ' ')
HAS_REFS=$([ -d "$CWD/.claude/refs" ] && echo "yes" || echo "no")
HAS_NAV=$([ -f "$CWD/.claude/skills/codebase-nav/SKILL.md" ] \
&& echo "yes" || echo "no")
cat <<EOF
<utility-index>
Available utilities — check BEFORE writing custom bash/grep/scripts.
Rule: if a skill covers your task, invoke it via the Skill tool first.
Global skills: github-cli · gstack · review · investigate · ship · qa
careful · guard · learn · office-hours · freeze · canary · checkpoint
document-release · land-and-deploy · retro · design-review · health
Global tools: ~/.claude/tools/atlassian (Jira/Confluence, no MCP)
~/.claude/skills/gstack/bin/ — QA/browser CLI tools
EOF
if [ "$HAS_NAV" = "yes" ]; then
echo "Codebase search: codebase-nav skill — pre-built grep patterns"
fi
if [ "$HAS_REFS" = "yes" ]; then
REFS=$(ls "$CWD/.claude/refs/"*.xml 2>/dev/null \
| xargs -I{} basename {} .xml | tr '\n' ' · ' | sed 's/ · $//')
echo "Refs (.claude/refs/): $REFS"
fi
if [ "$AGENT_COUNT" -gt 0 ] 2>/dev/null; then
echo "Agents (.claude/agents/): $AGENT_COUNT specialist agents"
fi
cat <<EOF
Project skills (.claude/skills/): check directory for available skills
</utility-index>
EOF
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.
- 3d ago First seen · 271 lines · 92 tokens per session scan B 2f3614702fa0
utility-setup is a skill published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 2,111 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…