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/luiseiman/dotforge/plugin-generatornpx skills add luiseiman/dotforge --skill plugin-generatorgit clone --depth 1 https://github.com/luiseiman/dotforgeWhat 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 | $0.00022 | $0.01866 |
| Opus 5 | $0.00011 | $0.00933 |
| Sonnet 5 | $0.00004 | $0.00373 |
| Haiku 4.5 | $0.00002 | $0.00187 |
Grade C, and why
plugin-generator scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf /)", How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Generator
Generate a distributable Claude Code plugin from the current project's dotforge configuration. The output is a standalone directory ready for claude --plugin-dir testing or marketplace submission.
Input
$ARGUMENTS may contain:
- Output directory path (default:
./dotforge-plugin/) --name <name>to override plugin name (default: project directory name)
Step 1: Validate source
Verify the current project has dotforge configuration:
CLAUDE.mdmust exist.claude/settings.jsonmust exist.claude/rules/should exist (warn if missing)
If missing, error: "No dotforge configuration found. Run /forge bootstrap first."
Step 2: Detect components
Scan the project's .claude/ directory and catalog:
Component scan:
CLAUDE.md → will become commands/context.md
.claude/rules/ → will become skills (one per rule with globs preserved)
.claude/hooks/ → will become hooks/hooks.json + script files
.claude/commands/ → will become commands/
.claude/agents/ → will become agents/ (if present)
.claude/settings.json → will extract deny list → settings.json
Show the scan results and ask for confirmation before generating.
Step 3: Generate plugin structure
Two shapes — pick by component count:
Flat (single-skill plugin, v2.1.142+) — when the plugin exposes ONE skill and no other components, put SKILL.md at the root. Claude Code surfaces it automatically since v2.1.142. Less boilerplate, no skills/ directory needed.
{output-dir}/
├── .claude-plugin/
│ └── plugin.json
├── SKILL.md (root-level, single skill)
├── README.md
└── LICENSE
Structured (default, multi-component plugin) — when the plugin ships ≥2 skills, or any combination of hooks, agents, commands:
{output-dir}/
├── .claude-plugin/
│ └── plugin.json
├── skills/
│ └── {rule-name}/
│ └── SKILL.md (one per rule, with globs as description context)
├── agents/ (copy from .claude/agents/ if exists)
│ └── *.md
├── hooks/
│ ├── hooks.json (converted from settings.json hook wiring)
│ └── *.sh (hook scripts)
├── commands/
│ └── *.md (from .claude/commands/)
├── settings.json (deny list only)
├── README.md (auto-generated usage guide)
└── LICENSE (copy from project root if exists)
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.
- 2d ago First seen · 258 lines · 22 tokens per session scan C c6e58f653b30
plugin-generator is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,866 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…