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.
git clone --depth 1 https://github.com/crabsmadethis/d2r-horadric-toolsWrote 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/commands/crabsmadethis/d2r-horadric-tools/d2r-build)<a href="https://agentmods.dev/commands/crabsmadethis/d2r-horadric-tools/d2r-build"><img src="https://agentmods.dev/badge/commands/crabsmadethis/d2r-horadric-tools/d2r-build/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/commands/crabsmadethis/d2r-horadric-tools/d2r-build"><img src="https://agentmods.dev/badge/commands/crabsmadethis/d2r-horadric-tools/d2r-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.00607 |
| Opus 5.5 | $0.00006 | $0.00243 |
| Sonnet 5.5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
d2r-build scanned grade A with 0 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
D2R Safe Build
Build character $ARGUMENTS using the chargen with full safety workflow.
Mandatory Steps
Execute these in order. Do NOT skip or combine steps.
1. Backup existing save
CHAR_NAME="$ARGUMENTS"
# Strip --phase flag if present for backup
CHAR_NAME=$(echo "$CHAR_NAME" | sed 's/ *--phase [0-9]*//')
SAVE_DIR="${D2R_SAVES:-$(python3 - <<'PY'
from d2r_chargen.config import SAVES
print(SAVES)
PY
)}"
D2S="$SAVE_DIR/${CHAR_NAME}.d2s"
if [ -f "$D2S" ]; then
cp "$D2S" "${D2S}.pre_build_bak"
echo "Backed up to ${D2S}.pre_build_bak"
else
echo "No existing save for ${CHAR_NAME} — fresh build"
fi
2. Run chargen build
python3 -m d2r_chargen build $ARGUMENTS
If the build fails, stop and diagnose. Do NOT proceed to scanning.
3. Run d2rdoctor scanner
python3 << 'PYEOF'
import sys
sys.path.insert(0, '<parent-of-d2r-tools>')
from d2r_scanner import run_scanner
run_scanner('$ARGUMENTS'.split()[0].lower())
PYEOF
4. Check scanner output
- Any hard error (returns False)? → Do NOT deploy. Fix the issue first.
- Checksum MISMATCH? → Recalculate before writing.
- LF INCONSISTENT? → Remove merc items or fix lf_count.
- Encoding issues? → Rebuild with corrected build_item().
Only proceed if scanner reports clean.
5. Verify and report
Tell the user:
- Build status (success/fail)
- Scanner results (clean/warnings/errors)
- Remind them: D2R caches saves at startup. Fully exit and relaunch D2R to see changes (Rule 7).
Rules Enforced
- Rule 3: Always backup before writing .d2s
- Rule 4: Always run d2rdoctor after every edit
- Rule 5: Always verify checksums
- Rule 10: Write to temp, verify, then overwrite (chargen handles this)
- Rule 12: Edit incrementally, test after each change
- Rule 17: Scanner hard errors are deployment blockers
- Rule 19: Investigate every remaining scanner error before closing
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.
- 2mo ago First seen · 78 lines · 16 tokens per session scan A 57eff8a01985
d2r-build is a command published in the GitHub repository crabsmadethis/d2r-horadric-tools (6 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 607 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
add-tool
Build a new UEFN Toolbelt tool named "$ARGUMENTS". Follow the tool-developer agent workflow exactly.
publish-check
Run a full pre-publish audit. Check everything before the user submits their island to Fortnite.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.