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/unbound-force/gaze/forgegit clone --depth 1 https://github.com/unbound-force/gazeWhat 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 | $0.00010 | $0.00522 |
| Opus 5 | $0.00005 | $0.00261 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
forge 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.
What it actually says
/forge
Decompose a task and spawn parallel workers.
Task
$ARGUMENTS
Workflow
- Initialize comms:
comms_init(project_path=".", task_description="Forge: <task>") - Check prior learnings:
hivemind_find(query="<task keywords>") - Decompose:
forge_decompose(task="<task>", context="<learnings>") - Create epic:
org_create_epic(epic_title="<task>", subtasks=[...]) - For each subtask:
forge_spawn_subtask(bead_id, epic_id, subtask_title, files) - Monitor: check
comms_inbox()every few minutes - Review:
forge_review(task_id, files_touched)for each completed worker - Complete:
forge_complete(bead_id, summary, files_touched) - Store learnings:
hivemind_store(information="...", tags="forge,<topic>")
Rules
- Always create a forge, even for small tasks
- Coordinator orchestrates, workers execute
- Workers reserve their own files via
comms_reserve - Check inbox regularly for blocked workers
- Review every worker's output before marking complete
- Store learnings after completion
Strategy Selection
Before decomposing, check historical success rates:
forge_get_strategy_insights(task="<task>")
Choose from: file-based, feature-based, risk-based, or auto.
Monitoring
While workers are active:
comms_inbox()— check for messages from workersforge_status(epic_id, project_key)— check worker progressorg_cells(status="in_progress")— see active cells
Completion
After all workers finish:
forge_complete(bead_id, summary, files_touched)— mark epic doneforge_record_outcome(bead_id, duration_ms, success)— record for learninghivemind_store(information="...", tags="forge,<topic>")— store learningsorg_sync()— persist state to git
Error Recovery
If a worker is blocked:
- Read the worker's message:
comms_read_message(message_id) - Acknowledge:
comms_ack(message_id) - Either unblock or reassign the subtask
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 · 68 lines · 10 tokens per session scan A 336fc4a6d56b
forge is a command published in the GitHub repository unbound-force/gaze (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 10 tokens to every session and 522 once invoked, about $0.0001 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.