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/malakhov-dmitrii/forgeWrote 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/malakhov-dmitrii/forge/forge)<a href="https://agentmods.dev/commands/malakhov-dmitrii/forge/forge"><img src="https://agentmods.dev/badge/commands/malakhov-dmitrii/forge/forge/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/malakhov-dmitrii/forge/forge"><img src="https://agentmods.dev/badge/commands/malakhov-dmitrii/forge/forge.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 | $0.00045 | $0.00303 |
| Opus 5.5 | $0.00018 | $0.00121 |
| Sonnet 5.5 | $0.00009 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00030 |
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 1mo 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
Route to the forge skill with the user's arguments.
If no arguments provided and a FINAL-PLAN exists in .omc/plans/, ask: plan new task or execute existing plan?
If forge.db has parked forges, mention them: "You have N parked forges. --list to see them, --resume to continue."
Flags:
--full— extended RESEARCH + mandatory spike on riskiest assumption--discuss— extended CLARIFY phase for vague input--plan-only— stop after FINAL-PLAN, don't execute--execute— load existing FINAL-PLAN, skip Plan Forge--park [reason]— save state to forge.db--resume [slug]— continue a parked forge--spawn "sub-task"— create child forge--switch [slug]— park current + resume another--list— show all forges with status--complete— mark done, record lesson--abandon [reason]— mark abandoned--no-docs— skip docs-refresh final stage
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.
- 1mo ago First seen · 24 lines · 45 tokens per session scan A 5b78dacb49a4
forge is a command published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 303 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
sprint
Scope-boxed sprints over the backlog: one active sprint, explicit carry-over, a close that refuses to hide unfinished work.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
chart
Chart an uncertain destination into a persistent map of decisions, then resolve one ticket per session.
kickoff-phase
Start a scoped chunk of a larger plan in a fresh session — interview the user first, then implement only that chunk.
align
Unified alignment command (--project, --docs, --retrofit, --content).