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/reset-projectnpx skills add luiseiman/dotforge --skill reset-projectgit 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 | $0.00025 | $0.01002 |
| Opus 5 | $0.00013 | $0.00501 |
| Sonnet 5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade C, and why
reset-project 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.
rm -rf .claude/ How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reset Project
Restore the current project's .claude/ directory completely to the dotforge template, from scratch.
Step 1: Confirm with the user (MANDATORY)
Show warning before proceeding:
╔══════════════════════════════════════════════════╗
║ RESET: .claude/ will be fully replaced ║
║ ║
║ The following will be lost: ║
║ - Customizations in settings.json ║
║ - Custom rules ║
║ - Custom hooks ║
║ - Any manually created files in .claude/ ║
║ ║
║ The following will be preserved: ║
║ - settings.local.json (not touched) ║
║ - CLAUDE.md (regenerated from template) ║
║ - CLAUDE_ERRORS.md (preserved if it exists) ║
║ ║
║ A backup will be created at .claude.backup-YYYY-MM-DD/ ║
╚══════════════════════════════════════════════════╝
Confirm reset? (yes/no)
If the user says "no", cancel immediately. DO NOT proceed without explicit confirmation.
Step 2: Detect stacks
Use detection rules from $DOTFORGE_DIR/stacks/detect.md.
Confirm detected stacks with the user.
Step 3: Create backup
- Create directory
.claude.backup-{YYYY-MM-DD}/in the project root - Copy ALL of
.claude/to the backup:cp -R .claude/ .claude.backup-$(date +%Y-%m-%d)/ - If
CLAUDE_ERRORS.mdexists, copy it separately (it will be restored afterwards) - Verify the backup exists and has content
Step 4: Re-run full bootstrap
- Delete the current
.claude/:rm -rf .claude/ - Run the
/bootstrap-projectskill in full from scratch - If
CLAUDE_ERRORS.mdexisted, restore the original file (not the empty template)
Step 5: Show diff between backup and new
Compare backup vs new .claude/:
═══ RESET COMPLETE ═══
New files (did not exist before):
+ .claude/rules/agents.md
+ .claude/agents/researcher.md
Updated files (differences from backup):
~ .claude/settings.json — 3 new permissions in allow
~ .claude/hooks/block-destructive.sh — 2 new patterns
Deleted files (were in backup, not in template):
- .claude/rules/custom-strategy.md
Preserved files:
= CLAUDE_ERRORS.md (restored from backup)
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 · 116 lines · 25 tokens per session scan C 51b886ecbf86
reset-project is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,002 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…