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/trackgit 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 | $0.00007 | $0.00643 |
| Opus 5 | $0.00003 | $0.00321 |
| Sonnet 5 | $0.00001 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
track 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/track — Feature Progress
Show where a feature stands, including what it owes.
Arguments
$1: Feature name (snake_case or will be converted)
Process
- Convert the feature name to snake_case and locate
docs/{feature_name}/05_progress_overview.md, falling back to{feature_name}/05_progress_overview.md. - If not found: "No plan found for '{feature_name}'. Run
/zforge:plan {name}to create one." - Read the overview, every phase file, and
decision_review.md.
Phase status comes from each phase file's > Status: header. There are no signals to scan for.
Report
## {Feature Name} — Progress
Phases: {completed}/{total}
Phase Name Status Checklist Evidence Last Activity
──────────────────────────────────────────────────────────────────────────────
1 Backend Schema COMPLETED 5/5 E2 / E2 2026-02-08
2 Backend API REPORTED 7/7 E2 / E2 * 2026-02-09
3 Frontend Types PENDING 0/4 — / E1 —
4 Frontend Pages PENDING 0/6 — / E4 —
5 Console Vocabulary PENDING 0/3 — / J2 —
* claimed, not re-run — Phase 2 is REPORTED
### Standing Flags (2 open)
- SF1 (Phase 5): E4 unmet across all UI phases — closes when a browser-executed run passes
- SF3 (Phase 7): live vendor calls deferred to a mock adapter — closes when a token exists
### Decisions awaiting review: 14 🟡
- Most recent: P7.1 — tri-state run status supersedes P2.8
### Open Items
- Phase 2 · question · migration ordering under concurrent writes — unresolved
The Evidence column reads achieved / required, and classes compare within their axis — an E row and a J row are not ranked against each other. A phase showing — / E4 has not yet demonstrated the class its plan asked for.
A completed phase showing anything below its requirement resolved that gap one of two ways: a standing flag against it, or reasoning in its ## Acceptance for why the shortfall was immaterial. Either is an answer. A shortfall with neither is the finding — say so, and name the row.
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 · 59 lines · 7 tokens per session scan A 2f642a4e6298
track is a command published in the GitHub repository Langerrr/zforge (10 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 643 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.