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/newgit clone --depth 1 https://github.com/ktoulgaridis/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 | $0.00030 | $0.01746 |
| Opus 5 | $0.00015 | $0.00873 |
| Sonnet 5 | $0.00006 | $0.00349 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
new 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 3d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:new — Bootstrap a new project
Create a fresh wiki repo + scaffold for an agent-driven engagement. This is the entry point: one command turns a project codename into a complete orchestration substrate.
Invocation
/forge:new <project-codename>
Example: /forge:new mojave, /forge:new acme-platform.
What this command does
Run an interactive wizard. Use AskUserQuestion (or sequential prompts) to gather config, then stamp.
Step 1 — Resolve the wiki destination
Ask:
"Where does the wiki repo live? Suggest options:
github.com/<your-user>/<project>-wiki(private)gitlab.<org>.com/<group>/<project>-wiki- Custom (paste full URL)"
Capture: wiki_remote_url, wiki_host (github / gitlab / bitbucket).
Step 2 — Tracker
Ask:
"Issue tracker?
- GitHub Issues
- GitLab Issues
- Jira (single board)
- Jira (multi-board, mapped to streams)
- Linear
- Asana"
Capture: tracker.type. Then per type:
- github → confirm same host as wiki, or different
- gitlab → confirm host (gitlab.com or self-hosted)
- jira-* → ask base URL (
https://<org>.atlassian.net); for multi-board, ask board keys per stream - linear → ask team ID
- asana → ask workspace + project IDs
Read the matching adapter at adapters/tracker/<type>.md to understand what other config the adapter needs.
Step 3 — SCM
Ask:
"SCM (where the code lives)?
- GitHub
- GitLab
- BitBucket"
Capture: scm.type, scm.org_or_user.
Step 4 — Streams
Default to A=backend, B=frontend, C=coordination, D=human. Offer to override:
"Streams (parallel work tracks)?
- Default (A=backend, B=frontend, C=coordination, D=human)
- Custom"
If custom, prompt for stream IDs + descriptions.
Step 5 — Methodology
Ask:
"Methodology (affects ticket templates + sizing units)?
- Scrum (sprints, story points)
- Kanban (continuous flow)
- RFC-first (design doc before tickets)
- Custom (use sensible defaults)"
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.
- 3d ago First seen · 215 lines · 30 tokens per session scan A 31568aac6ba0
new is a command published in the GitHub repository ktoulgaridis/forge (10 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 1,746 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.