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 commands/marcusgoll/spec-flow/create-custom-toolinggit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWhat 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 | $0.00021 | $0.02615 |
| Opus 5 | $0.00010 | $0.01307 |
| Sonnet 5 | $0.00004 | $0.00523 |
| Haiku 4.5 | $0.00002 | $0.00262 |
Grade C, and why
create-custom-tooling scanned grade C with 2 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 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.
- Hooks: !`cat .claude/settings.json 2>/dev/null | grep -A5 '"hooks"' || echo "none"` Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Skills: !`ls .claude/skills/project-custom/ 2>/dev/null || echo "none"` How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-custom-tooling — Pattern-Based Tooling Generation
Purpose: Transform recurring code patterns detected during /audit-workflow into reusable project-specific skills, slash commands, or hooks.
Command: /create-custom-tooling [skill|command|hook] [pattern-name] [--from-audit <epic-slug>]
When to use:
- After
/audit-workflowidentifies recurring patterns (3+ occurrences) - When you notice repetitive code structures across features
- To codify project-specific conventions into reusable tools
Check for audit reports:
!ls -la epics/*/audit-report.xml 2>/dev/null | head -5
Existing custom tooling:
- Skills: !
ls .claude/skills/project-custom/ 2>/dev/null || echo "none" - Commands: !
ls .claude/commands/project-custom/ 2>/dev/null || echo "none" - Hooks: !
cat .claude/settings.json 2>/dev/null | grep -A5 '"hooks"' || echo "none"
Tooling Types:
- Skill: Reusable knowledge/templates that Claude loads on-demand (e.g., service boilerplate, CRUD patterns)
- Command: Executable slash command for specific actions (e.g., /generate-crud, /create-migration)
- Hook: Automated triggers on tool events (e.g., auto-format on file save, validate on commit)
Step 1: Parse Arguments and Determine Mode
Parse $ARGUMENTS:
const args = "$ARGUMENTS".trim().split(/\s+/);
const toolingType = args[0]; // skill, command, or hook
const patternName = args[1]; // e.g., "service-boilerplate"
const fromAuditFlag = args.includes('--from-audit');
const epicSlug = fromAuditFlag ? args[args.indexOf('--from-audit') + 1] : null;
If no arguments provided, enter discovery mode:
{
"question": "What type of tooling do you want to create?",
"header": "Tooling Type",
"multiSelect": false,
"options": [
{"label": "Skill", "description": "Reusable knowledge/templates (e.g., service boilerplate)"},
{"label": "Command", "description": "Executable slash command (e.g., /generate-crud)"},
{"label": "Hook", "description": "Automated trigger on tool events (e.g., auto-lint)"}
]
}
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 · 407 lines · 0 tokens per session scan C 18c95c7fdd98
create-custom-tooling is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 2,615 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sync-linear
Sync current work with Linear ticket status.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
auto-run
PitWay: Manage auto-run authorization for automatic task continuation.
task-integrate
PitWay: Apply a dispatched task's worktree commit to the main tree.
milestone-list
PitWay: List every milestone with a concise one-line status.
setup
Install the claude-pace statusline bundled with this plugin.