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/plangit 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 | $0.00010 | $0.01899 |
| Opus 5 | $0.00005 | $0.00949 |
| Sonnet 5 | $0.00002 | $0.00380 |
| Haiku 4.5 | $0.00001 | $0.00190 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Plan
Decompose approved specifications into ordered task frontiers with dependency DAGs, token estimates, and repo tags.
First-Run Wizard (R004.AC3)
Before anything else, fire the one-shot token-reduction wizard. Idempotent — prints once on first install, then no-ops forever. Suppressed when /forge:watch is rendering its own banner (R004.AC6).
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-wizard.cjs" --forge-dir .forge
Pre-flight Check
- Verify
.forge/exists. If it does not, stop and tell the user:.forge/not found. Run/forge brainstormfirst to generate specifications. - Verify
.forge/specs/contains at least onespec-*.mdfile withstatus: approvedin its frontmatter. If none found, stop and tell the user:No approved specs found in
.forge/specs/. Run/forge brainstormto create specs, then approve them before planning.
Parse Arguments
Parse flags from $ARGUMENTS:
| Flag | Default | Description |
|---|---|---|
--filter NAME |
(all specs) | Only plan specs whose domain matches NAME |
--depth quick|standard|thorough |
(auto-detect) | Task granularity level |
--repos REPO1,REPO2 |
(all configured repos) | Limit planning to specific repos |
If --depth is not provided and the project config has auto_detect_depth: true:
- Dispatch a forge-complexity agent (via
Agenttool) to analyze the specs and recommend a depth level. - Use the agent's recommendation unless the user overrides.
- If auto-detection is disabled in config, fall back to the
depthvalue in.forge/config.json(default:standard).
Read Configuration
- Read
.forge/config.jsonfor project settings (repos, depth, cross_repo_rules). - Read
.forge/capabilities.jsonif it exists, to inform the planner about available MCP servers and skills.
Auto-Detect Project Context
These checks run automatically before planning. Do not skip them.
Knowledge graph: First check if graphify-out/graph.json already exists. If not, check if graphify is installed:
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 · 145 lines · 10 tokens per session scan A 3a8b56226947
plan is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,899 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 2026-08-30.
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.