agentmods.dev

cycle

A command that runs a complete product-work cycle from the project's current state. It chooses Founder mode when the project has a thesis file, or PM mode when it has an identity file, then runs the matching research, planning, building and release stages.

In plain words
What is it for?
Use it to run a full discovery-to-testing cycle for an early product, or a feedback-to-release cycle for an existing one. It requires either THESIS.md or IDENTITY.md in the project, and asks which mode to use if both exist.
Why use it?
It removes the need to remember which project step comes next and keeps the work moving through the framework's required stages. It pauses after each stage so a person can review the result before continuing.

Command

6 3mo ago A scan 56 tokens original MIT
View the source file dormstern/forge
Install

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.

agentmods
npx agentmods add commands/dormstern/forge/cycle
Clone the repo
git clone --depth 1 https://github.com/dormstern/forge
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.00458
Opus 5 $0.00028 $0.00229
Sonnet 5 $0.00011 $0.00092
Haiku 4.5 $0.00006 $0.00046

Measured yesterday against content hash 8c93f1b8a224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cycle 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.

commands/cycle.md · 35 lines

What it actually says

/forge:cycle — Full cycle, auto-routed

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 orchestrate a complete cycle from start to finish, pausing at every human checkpoint defined by the framework.

Mode detection

  • If THESIS.md exists at the project root → Founder mode: run /forge:scout, then /forge:interrogate, then /forge:synthesize, then /forge:graduate (12-criteria check). Pause at each phase boundary.
  • If IDENTITY.md exists → PM mode: run /forge:harvest, then /forge:shape, then /forge:build, then /forge:ship. Pause at each phase boundary.
  • If both exist → ask the user which mode to run.
  • If neither exists → tell the user to run /forge:init first.

Pausing rules

After every phase, PAUSE and present a short summary. Do not advance until the user confirms. The framework's discipline depends on this — it's not optional.

Phase summaries should be ≤200 words and end with: "Run /<next-command> to advance, or send feedback first."

State file rules

  • Re-read the relevant state files between phases. Do not carry context forward across phase boundaries.
  • Persist updates to state files as you go (don't batch).
  • Announce phase transitions explicitly: --- PHASE: <name> ---

Reference

Changes

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.

  1. yesterday First seen · 35 lines · 56 tokens per session scan A 8c93f1b8a224

Subscribe to this mod's changes

cycle is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 458 once invoked, about $0.0003 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.

Git and workflowResearchTesting
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

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.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

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.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens