comet-build

comet-build is a skill for Claude Code, Codex from rpamis/comet. It costs 36 tokens per session (4,441 once invoked), scanned A, original, MIT.

A build phase in the Comet software-change workflow. It starts after a design document and active change already exist, then turns the approved plan into code.

In plain words
What is it for?
Verifying the workflow state, creating an implementation plan, choosing whether to use a helper agent, and completing the unchecked tasks in the change plan.
Why use it?
It helps keep implementation tied to an existing plan and recorded project state. Entry checks and task tracking reduce the chance of skipping prerequisites or repeating completed work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Verifying the workflow state, creating an implementation plan, choosing whether to use a helper agent, and completing the unchecked tasks in the change plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rpamis/comet/comet-classic-039-build
About the project

Comet is a resumable workflow and skill platform for coding tasks, covering requirements work as well as skill creation, evaluation, and release. It supports separate Native and Classic workflows and can coordinate implementation and verification across isolated Git worktrees. The catalogue contains skills and instructions that implement Comet-related workflows.

rpamis/comet · 2,988 stars · on GitHub · docs.comet.rpamis.com

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.

Any agent
npx skills add rpamis/comet --skill comet-classic-039-build
Clone the repo
git clone --depth 1 https://github.com/rpamis/comet

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for comet-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/rpamis/comet/comet-classic-039-build/github.svg)](https://agentmods.dev/skills/rpamis/comet/comet-classic-039-build)
Your own site
<a href="https://agentmods.dev/skills/rpamis/comet/comet-classic-039-build"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-classic-039-build/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for comet-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/rpamis/comet/comet-classic-039-build"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-classic-039-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00036 $0.04441
Opus 5 $0.00018 $0.02220
Sonnet 5 $0.00007 $0.00888
Haiku 4.5 $0.00004 $0.00444

Measured 10d ago against content hash 91160c11f7ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

comet-build 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 10d 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.

eval/local/skills/benchmarks/039-release/comet-classic-039-build/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comet Phase 3: Plan and Build (Build)

Prerequisites

  • Design Doc has been created (Phase 2 complete)
  • Active change exists

Steps

0. Entry State Verification (Entry Check)

Execute entry verification:

COMET_ENV="${COMET_ENV:-$(find . "$HOME"/.*/skills "$HOME/.config" "$HOME/.gemini" -path '*/comet/scripts/comet-env.sh' -type f -print -quit 2>/dev/null)}"
if [ -z "$COMET_ENV" ]; then
  echo "ERROR: comet-env.sh not found. Ensure the comet skill is installed." >&2
  return 1
fi
. "$COMET_ENV"
"$COMET_BASH" "$COMET_STATE" check <name> build

Proceed to Step 1 after verification passes. The script outputs specific failure reasons when verification fails.

Idempotency: All build phase operations can be safely re-executed. Read .comet.yaml phase field to confirm still in build, read plan header base-ref, then use grep -n '\- \[ \]' tasks.md | head -1 to find the first unchecked task. Already-committed tasks must not be re-committed.

1. Create Plan (Subagent Offload)

Create the implementation plan through a subagent, avoiding planning skill occupying main session context. Plan files and execution feedback must use the language of the user request that triggered this workflow.

Subagent instructions:

You are an implementation planning expert. Create an implementation plan based on the following inputs:

  1. Immediately execute: Use the Skill tool to load the Superpowers writing-plans skill. Skipping this step is prohibited. After the skill loads, ARGUMENTS must include: Language: Use the language of the user request that triggered this workflow
  2. Read the Design Doc (technical design document under docs/superpowers/specs/)
  3. Read openspec/changes/<name>/tasks.md (task boundaries)
  4. Follow the skill's guidance to create the plan

Plan requirements:

  • Save to docs/superpowers/plans/YYYY-MM-DD-<feature>.md
  • Reference design document, break down into executable tasks
  • Plan file header must contain associated metadata:

Read the full file on GitHub · 305 lines

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. 10d ago First seen · 305 lines · 36 tokens per session scan A 91160c11f7ba

Subscribe to this mod's changes

comet-build is a skill published in the GitHub repository rpamis/comet (2,988 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 4,441 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 2026-08-30.

Related

Other skills, from other repositories

agent-spec-estimate

An effort-estimation method for agent-spec Task Contracts, which are structured descriptions of software work. It estimates work in rounds, meaning cycles of an AI agent doing and checking tasks.

ZhangHanDong/agent-spec · 116 tokens

agent-spec-intent-compiler

Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human to resolve requirement ambiguity before task spec generation.

ZhangHanDong/agent-spec · 42 tokens

codex-setup

Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.

sd0xdev/sd0x-harness · 65 tokens

create-request

Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…

sd0xdev/sd0x-harness · 112 tokens

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…

sd0xdev/sd0x-harness · 131 tokens

remind

A correction helper that checks which project rules or required steps were missed and loads the relevant guidance.

sd0xdev/sd0x-harness · 157 tokens