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/ktoulgaridis/forge/emitgit clone --depth 1 https://github.com/ktoulgaridis/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/ktoulgaridis/forge/emit)<a href="https://agentmods.dev/commands/ktoulgaridis/forge/emit"><img src="https://agentmods.dev/badge/commands/ktoulgaridis/forge/emit.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 | $0.00043 | $0.02096 |
| Opus 5 | $0.00022 | $0.01048 |
| Sonnet 5 | $0.00009 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
emit 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:emit — Emit an org-owned agent harness
The generative entry point of forge v2. /forge:new opens a project; /forge:emit
mints the org's package: a standalone Claude Code plugin that aligns the harness to
how this org works, owned entirely by the org.
The cardinal rule. The emitted package is org-owned. forge's identity — the name "forge", the maintainer, the upstream repo URL — must never appear in the output. The org installs and distributes its package as its own; forge is the mill, not a runtime dependency. Step 5 below fails the emit if any generator identity leaks through.
Invocation
/forge:emit [--config <path>] [--out <dir>] [--target {claude-code,opencode}]
--config— the org-tier config. Defaults to./.forge.org.yaml(see.forge.org.example.yamlfor the shape).--out— where to write the package. Defaults to../<plugin.name>.--target— the host to package for. Defaults toclaude-code(a Claude Code plugin:skills/+agents/+hooks/+.claude-plugin/).opencodeemits an opencode configuration (opencode.json+agent/+command/+skill/) from the same config and requires theopencode:block. The skill bodies are shared byte-for-byte across targets except at the{{#TARGET_*}}conditionals and the host-noun scalars.
What this command does
Run it
The whole pipeline below is implemented by the shared renderer — the same
engine /forge:new uses (lib/render.py), driven for the org tier by lib/emit.py:
uv run --with pyyaml python lib/emit.py \
--config .forge.org.yaml --out ../<plugin.name>
lib/emit.py performs steps 1–5; step 6 is claude plugin validate. Read on for
what each step guarantees (and what to do when one fails).
1. Load + validate the org config
lib/emit.py reads .forge.org.yaml and requires: org.name/org.slug, the full
plugin: identity block (name, version, description, author.name, author.url,
homepage, license), org_wiki: (incl. prime_reads), tracker:, and agents:. If
any identity field is missing or still carries an example value (acme, Acme,
janedoe, example), it stops — never emit with placeholder identity.
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 · 169 lines · 43 tokens per session scan A c88115cb1729
emit is a command published in the GitHub repository ktoulgaridis/forge (10 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 2,096 once invoked, about $0.0002 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.