An automated software delivery workflow that moves a feature from written requirements through implementation, review, and release preparation. It includes TDD, meaning tests are written before the code that makes them pass.

Use it to create an approved specification, implement the feature with tests, audit the result, and prepare it to ship.

It organizes several development steps into one repeatable process and checks requirements, code quality, security, and test coverage along the way.

orbit — Skill for Claude Code and Codex by epicsagas

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 epicsagas/plugins --skill orbit

Clone the repo

git clone --depth 1 https://github.com/epicsagas/plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/epicsagas/plugins/orbit/github.svg)](https://agentmods.dev/skills/epicsagas/plugins/orbit)

Your own site

<a href="https://agentmods.dev/skills/epicsagas/plugins/orbit"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/orbit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/epicsagas/plugins/orbit"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/orbit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 614 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00614
Opus 5	$0.00029	$0.00307
Sonnet 5	$0.00012	$0.00123
Haiku 4.5	$0.00006	$0.00061

Measured 5d ago against content hash a1b664270e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

orbit 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 5d 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.

.hermes/epic/skills/orbit.SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous software delivery pipeline: spec → go → audit → ship. One command takes a feature from idea to PR.

Usage

/orbit <feature description>

Pipeline phases

Phase 1 — Spec

Write a numbered requirements + acceptance criteria document.

Use harness_mem_recall to surface relevant past decisions and patterns
Analyze the codebase to understand current architecture
Produce a SPEC.md with numbered requirements (REQ-1, REQ-2, …) and acceptance criteria (AC-1.1, …)
Present spec to user for approval before proceeding

Phase 2 — Go

Implement the approved spec via TDD.

For each requirement, write a failing test first
Implement minimum code to pass the test
Run tests after each change — no progress without green tests
Use harness_mem_add to record key decisions made during implementation

Phase 3 — Audit

Parallel review across 3 dimensions.

Code quality — unused imports, dead code, naming, complexity
Security — input validation, auth checks, secret exposure
Test coverage — missing edge cases, uncovered error paths
Output PASS / WARN / FAIL per dimension
Fix all FAIL items, address WARN items if trivial

Phase 4 — Ship

Create PR and verify CI passes.

Create a feature branch if not already on one
Commit all changes with conventional commit messages
Push branch and create PR with spec summary
Monitor CI — if it fails, fix and re-push
Report final status

Decision: which phases to run

User request	Phases
"orbit" or "full pipeline"	All 4 phases
"just spec it"	Phase 1 only
"implement this spec"	Phase 2–4
"audit and ship"	Phase 3–4

Error handling

Situation	Action
Spec rejected by user	Revise spec, do not proceed to Go
Tests failing after 3 attempts	Stop, report to user, ask for guidance
Audit finds security FAIL	Must fix before shipping
CI fails	Auto-fix once, then report to user

Memory integration

Read the full file on GitHub · 76 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.

5d ago First seen · 76 lines · 58 tokens per session scan A a1b664270e88

Subscribe to this mod's changes

orbit is a skill published in the GitHub repository epicsagas/plugins (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 614 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 2026-09-05.

Claude Code Planning TDD Testing ai-agent developer-tools marketplace plugins

principles

Metric literacy for what this plugin reports: what cyclomatic complexity, cognitive complexity, Halstead difficulty, lines per file, duplication, coverage, CRAP, and type debt mean, and what none of them can tell you. Four reference files carry the definitions and what each collector computes, each bundled reference…

melodic-software/claude-code-plugins · 218 tokens

codex-pipeline

Runs a dev task through the cross-model codex pipeline — spec and held-out tests written here, implementation by mcpcodexcodex, fresh-context diff review, fixes via mcpcodexcodex-reply. Use when the user asks to run the codex pipeline or have Codex or GPT implement something — e.g. "run this through codex", "use the…

V-Songbird/foundry · 152 tokens

systematic-debugging

Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.

shrwnsan/vibekit-claude-plugins · 54 tokens

orbit