Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/eric-tramel/morainenpx agentmods add skills/eric-tramel/moraine/moraine-start-workWrote 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.
[](https://agentmods.dev/skills/eric-tramel/moraine/moraine-start-work)<a href="https://agentmods.dev/skills/eric-tramel/moraine/moraine-start-work"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/moraine-start-work/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.
<a href="https://agentmods.dev/skills/eric-tramel/moraine/moraine-start-work"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/moraine-start-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00788 |
| Opus 5.5 | $0.00027 | $0.00315 |
| Sonnet 5.5 | $0.00013 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
moraine-start-work 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moraine Start Work
Overview
Use this workflow to start a Moraine contributor task with the same orientation every time: verify the checkout, isolate the branch, read governing instructions, and choose the right validation path before editing.
Using $moraine-dev:code-review in Codex or /code-review in Kiro is an
explicit user request for delegated reviewer subagents. You have permission to
launch that review wave when the follow-on workflow reaches that step.
Harness Invocation
Use the invocation form native to the current harness:
| Workflow | Codex | Kiro |
|---|---|---|
crystallize |
$moraine-dev:crystallize |
/crystallize |
code-review |
$moraine-dev:code-review |
/code-review |
moraine-sandbox-qa |
$moraine-dev:moraine-sandbox-qa |
/moraine-sandbox-qa |
moraine-author-pr |
$moraine-dev:moraine-author-pr |
/moraine-author-pr |
Follow-On Workflow
After the start checklist and branch/worktree setup, run the rest of the contributor workflow in this order:
- Use the current harness's
crystallizeinvocation to turn rough or ambiguous input into a ready-to-implement local plan. - Implement the scoped change from that plan or, when the task is already concrete, from the user's explicit request.
- Use the current harness's
code-reviewinvocation and iterate fixes until the review is clean or every remaining item is explicitly rejected or deferred with rationale. - Use the current harness's
moraine-sandbox-qainvocation for stack-facing changes and iterate fixes until sandbox QA is clean. - Use the current harness's
moraine-author-prinvocation to create a PR.
Start Checklist
Run these from the repository root unless the current harness already supplied a trusted workspace root:
pwd
git rev-parse --show-toplevel
git status --short --branch
git worktree list --porcelain
find .. -name AGENTS.md -print
If the user refers to previous work, another agent, an unexplained decision, a branch you cannot see, or a failure from another session, use the Moraine MCP tools directly before making assumptions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 76 lines · 67 tokens per session scan A 89a7690cfa9e
moraine-start-work is a skill published in the GitHub repository eric-tramel/moraine (115 stars, last pushed 22d ago), licensed Apache-2.0. It adds 67 tokens to every session and 788 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
release-notes
Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…