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/dormstern/forge/statusgit clone --depth 1 https://github.com/dormstern/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 | $0.00034 | $0.01056 |
| Opus 5 | $0.00017 | $0.00528 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
status 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:status — Current phase + state snapshot
Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.
You produce a one-screen summary of where the user is in their cycle.
Behavior
-
Detect mode.
THESIS.mdexists → Founder.IDENTITY.mdexists → PM. Both → ask. Neither → tell the user to run/forge:init. -
Render a status card. Compact, one screen, monospace alignment.
PM-mode status card
Render the card with one interpretive sentence above each section that turns the numbers into plain English:
═════════════════════════════════════════════════════
CYCLE STATUS — PM mode
═════════════════════════════════════════════════════
Your product (Identity v{N}):
WHO: {one-line WHO from IDENTITY.md}
JOB: {one-line JOB}
NEVER: {one-line NEVER}
You're in cycle v{next-version}, phase {HARVEST|SHAPE|BUILD|SHIP}.
Signals harvested this cycle: {N} ({HIGH}H / {MED}M / {LOW}L). {invalidate-count interpretation: "1 invalidates your current thesis — review before /forge:shape" or "none invalidate the thesis"}.
Release plan: {features-count} features queued, {debt} debt items, {kill} killed by the 10% Delete Rule.
Build progress: {done}/{total} features done, {blocked} blocked. {blocked > 0 ? "Blocked features hit 3 resets — likely scope or test issues; investigate features.json." : "No blockers."} Avg quality {score}/10.
Last 3 releases (avg quality {avg}/10 — {avg ≥ 8 ? "trending healthy" : avg ≥ 6 ? "watch for stabilization" : "stabilization needed"}):
v{X-2} {score}/10
v{X-1} {score}/10
v{X} {score}/10 ← shipped {date}
Stabilization triggers: {fired-list or "none firing — keep building"}.
Recent drift ({date}): {recommendation interpretation: "DISCUSS — surface honeycomb-comparison at next /forge:shape" or "CONTINUE — no action"}
⚡ Next: /{harvest|shape|build|ship|drift} — {one-sentence why this is the next step}.
═════════════════════════════════════════════════════
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.
- yesterday First seen · 83 lines · 34 tokens per session scan A 5505eb7a8723
status is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 1,056 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.