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/langerrr/zforge/plangit clone --depth 1 https://github.com/Langerrr/zforgeWhat 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 | $0.00008 | $0.03123 |
| Opus 5 | $0.00004 | $0.01562 |
| Sonnet 5 | $0.00002 | $0.00625 |
| Haiku 4.5 | $0.00001 | $0.00312 |
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan — Feature Planning
You are the zforge planner. You do not run the discovery conversation — superpowers:brainstorming does, or ce:brainstorm, or the user arrives with a spec. Your job starts where that leaves off: resolve a completeness contract, then write the artifact tree that phases will execute from.
Arguments
$1— feature name (converted to snake_case for the directory)--spec <file>— an external requirements document to use as the base--kind requirements|implementation— what this session terminates at. Inferred and proposed when absent
Pre-flight
- Resolve the feature docs path:
docs/{feature_name}/unless the project uses a different convention — checkCLAUDE.mdand the existing tree before assuming. - If the directory exists, read
05_progress_overview.mdand ask whether to re-plan or continue. - Load the
template-conventionsskill. It is the source of truth for structure, ownership and naming. - If the conversation has not been through brainstorming and no
--specwas given, say so and runsuperpowers:brainstormingfirst. Planning an unexamined request produces a phase graph nobody can execute. - Resolve the output kind, because it selects which groups are on the contract:
| Kind | Terminates at | Groups |
|---|---|---|
implementation |
a phase tree agents execute | A · B · C · D |
requirements |
a specification a later session plans from | A · B |
Where --kind was not given, infer it and state the inference as a proposal — the ladder below governs this choice too. Infer requirements when nothing buildable is in front of you: the work is a product definition, an architecture direction or a domain model, and no phase could yet name a file it would change. Infer implementation when a concrete change is on the table. Say which you chose in one line and let the user correct it.
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 · 175 lines · 0 tokens per session scan A 455c1865c564
plan is a command published in the GitHub repository Langerrr/zforge (10 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 3,123 once invoked, about $0.0000 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
decision
Record one architecture decision in the decision log (what, why, what was rejected, when to revisit) / Registra una decisión de arquitectura en la bitácora de decisiones.
gate
Run the SDD gate (policy + approval + consistency) and record consent before implementation / Ejecuta la compuerta SDD y registra consentimiento antes de implementar.
tutor
Learn SDD conversationally - the agent becomes your tutor, by levels, with real validation as the grader / Aprende SDD conversando - el agente es tu tutor, por niveles, con validación real como corrector.
close
Validate and close the session with the SDD output contract / Valida y cierra la sesión con el contrato de salida SDD.
new
Start a project with SDD - capture the idea and prepare the first spec / Inicia un proyecto con SDD - captura la idea y prepara la primera spec.
help
Diagnose the current SDD stage and tell the user the exact next step / Diagnostica la etapa SDD actual y da el siguiente paso exacto.