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/luiseiman/dotforge/forge-ultracode-checkgit clone --depth 1 https://github.com/luiseiman/dotforgeWrote 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/luiseiman/dotforge/forge-ultracode-check)<a href="https://agentmods.dev/commands/luiseiman/dotforge/forge-ultracode-check"><img src="https://agentmods.dev/badge/commands/luiseiman/dotforge/forge-ultracode-check.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00554 |
| Opus 5 | $0.00026 | $0.00277 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
forge-ultracode-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Decide whether ultracode mode is justified RIGHT NOW for this working tree.
-
Resolve project tier
- Read
registry/projects.local.yml(or.forge-manifest.jsonat repo root, or$DOTFORGE_DIR/registry/projects.local.yml) - Match entry by
cwd→ extractultracode_tier(light|standard|heavy|production) - If no match or field absent → default
standard, note "unregistered project"
- Read
-
Read working state
git status --short→ count files modified (M) and staged (A/M cached)git diff --stat HEAD→ lines added/removed- Read
.claude/session/last-startup.md→ recent edits + active task hint - Note presence of high-risk surfaces: migrations, auth, payments, infra IaC, schema files,
template/hooks/,settings.json.partial
-
Apply the 5 canonical criteria (from
domain/workflow-and-ultracode-policy.md)- C1 Blast radius: ≥3 files OR >200 LOC changed → +1
- C2 Domain risk: tier ≥ heavy, OR touches auth/payments/migrations/infra/schema/security → +1
- C3 Ambiguity: ≥2 valid approaches with real tradeoffs (infer from task hint) → +1
- C4 Reversibility: hard to undo (prod migration, force-push, schema drop, live trade) → +1
- C5 Prior failure: sonnet attempted and failed, OR
CLAUDE_ERRORS.mdshows repeat in this area → +1
-
Output verdict
Ultracode recommendation: ON | CONSIDER | OFF
Score: N/5 (tier: <tier>, files: <n>, LOC: ±<n>)
Triggered: C2 (auth touched), C4 (migration irreversible)
Reasoning: <2-3 lines citing which criteria fired and why>
Mapping: score ≥3 → ON · score 2 → CONSIDER · score ≤1 → OFF. Override to ON if C2+C4 both fire regardless of total — irreversible touch on a risk surface always warrants adversarial verify.
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.
- 4d ago First seen · 37 lines · 51 tokens per session scan A 00f88097e682
forge-ultracode-check is a command published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 554 once invoked, about $0.0003 per session on Opus 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
get-to-work
Autonomous ops work. Args: [mode] [repeat]. Modes: tasks | opps | full | escalating (default). Repeat: cycle (keep going, default) | once (single pass). Run this before stepping away from an ops repo.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
recap
Summarize what happened in the project since a given date. Produces a short lead on what's different now, backed by tables and lists covering completed work, state changes, backlog movement, and key decisions. Use when the user wants to catch up on project activity, review recent progress, or generate a status update…
whats-next
Generate an executive overview of the project. Synthesizes state, backlogs, and recent plans into a ranked action plan answering "What should we do next?".
batch-plan
Create a batch of ops plans continuously without user input, storing any user questions in a .md file to be processed with the user afterwards. Do NOT invoke this yourself! Should only be invoked by the user.
batch-execute
Execute a batch of ops plans continuously without user input, storing any issues and user questions in a .md file to be processed with the user afterwards. Do NOT invoke this yourself! Should only be invoked by the user.