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/lucasduys/forge/statusgit clone --depth 1 https://github.com/LucasDuys/forgeWhat 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 | $0.00005 | $0.01063 |
| Opus 5 | $0.00003 | $0.00531 |
| Sonnet 5 | $0.00001 | $0.00213 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Status
First-Run Wizard (R004.AC3)
Before anything else, fire the one-shot token-reduction wizard. Idempotent — prints once on first install, then no-ops forever. Suppressed when /forge:watch is rendering its own banner (R004.AC6).
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-wizard.cjs" --forge-dir .forge
Present a unified Forge dashboard. If the user passed --json anywhere in the
command arguments, emit machine-readable JSON instead of the formatted view.
Data sources
Run these commands and combine their output. Always pass --forge-dir .forge.
node ${CLAUDE_PLUGIN_ROOT}/scripts/forge-tools.cjs headless query --forge-dir .forge --json- Authoritative snapshot from T011: phase, current_task, completed/remaining task counts, lock_status, active_checkpoints, last_error, token totals.
node ${CLAUDE_PLUGIN_ROOT}/scripts/forge-tools.cjs budget-status --forge-dir .forge --json- Per-task token ledger plus session budget summary and iteration count.
- Read
.forge/state.mddirectly for fields the headless query does not surface (autonomy, depth, blocked_reason, last heartbeat timestamp). - Read
.forge/capabilities.jsonif it exists to count MCP servers and skills. - Check whether
.forge/.forge-loop.jsonexists -- if so, the autonomous loop is currently active. - Check whether
.forge/.forge-debug.logexists and is non-empty. - List
.forge/checkpoints/*.json(if the directory exists) to surface any in-progress task checkpoints.
JSON mode
If the user passed --json, output a single JSON object with these top-level
keys merged from the sources above. Do not pretty-format with extra commentary.
{
"phase": "...",
"spec": "...",
"current_task": "...",
"task_status": "...",
"iteration": N,
"max_iterations": N,
"tasks": { "completed": N, "remaining": N, "total": N },
"tokens": { "used": N, "budget": N, "percent": N, "remaining": N },
"per_task_budgets": [ ... from budget-status ... ],
"lock_status": "free|held|stale",
"active_checkpoints": N,
"last_error": "...",
"depth": "...",
"autonomy": "...",
"loop_active": true|false,
"debug_log_has_entries": true|false,
"blocked_reason": "..." | null,
"capabilities": { "mcp_servers": N, "skills": N }
}
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 · 109 lines · 5 tokens per session scan A a7d197c77e5f
status is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 1,063 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
handoff
Run the full handoff workflow — specs, measurements, assets, states, and a QA checklist — and output a developer-ready package.
discover
Run a full user research cycle — persona creation, empathy mapping, and journey mapping for a product or feature.
test-plan
Run the full usability study workflow — research questions, participant criteria, tasks, metrics, and facilitation guide.
eg-new-feature
Build a new feature using the elephant/goldfish workflow — design doc, goldfish design check, implement, review, validate.
eg-precommit-review
Run the pre-commit independent-reviewer loop on the current branch's pending changes.
eg-fix-bug
Fix a bug using the elephant/goldfish workflow — problem doc, goldfish diagnosis check, failing test, fix, review, validate.