repo-native-alignment: Agent for Claude Code

.claude/agents/dev-pipeline.md

dev-pipeline is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 33 tokens per session (775 once invoked), scanned A, original, MIT.

A guided development workflow that takes a change from defining the problem to merging the finished code. It uses GitHub issues and pull requests to track the work.

In plain words
What is it for?
Use it to frame a GitHub issue, create a working branch and draft pull request, explore solutions, carry out the change, and prepare it for merging.
Why use it?
It prevents coding from starting without a clear problem and agreed success criteria. It also keeps progress visible while possible solutions are explored and implemented.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code how to work on repo-native-alignment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-horizon-labs/repo-native-alignment/main/.claude/agents/dev-pipeline.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

Made for: Claude Code.

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 dev-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/dev-pipeline/github.svg)](https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/dev-pipeline)
Your own site
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/dev-pipeline"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/dev-pipeline/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 dev-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/dev-pipeline"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/dev-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00775
Opus 5 $0.00016 $0.00387
Sonnet 5 $0.00007 $0.00155
Haiku 4.5 $0.00003 $0.00077

Measured 8d ago against content hash cf1f4d0723fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dev-pipeline 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 8d 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.

.claude/agents/dev-pipeline.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.

/dev-pipeline

problem-statement → solution-space → execute → ship. Four phases, each gates the next.

Arguments

/dev-pipeline <issue-number-or-description>

Session File

Write all phase outputs to .oh/sessions/<issue-number>-dev.md. Include an ## RNA Tool Friction Log table — every Grep/Read used for code navigation after scan is a skipped friction event.


Phase 1: GitHub Issue (problem-statement)

Create the issue FIRST. It is the anchor for everything.

  • If issue number given: read it, check for clear problem statement + acceptance criteria. Reframe with oh-problem-statement agent if needed.
  • If description given: spawn oh-problem-statement agent (do not skip or inline), then gh issue create with the output.

Gate: No Phase 2 without acceptance criteria on a GitHub issue.


Phase 2: Branch + Draft PR → Solution Space

Push the PR IMMEDIATELY — before solution exploration. Progress must be visible from the start.

  1. git checkout -b <issue-number>-<slug> main
  2. git commit --allow-empty -m "wip: <title>"git push -u origingh pr create --draft
  3. Then spawn oh-solution-space agent. Bias against Local Optimum solutions — if it involves intricate coordination or new lock protocols, step up to Reframe/Redesign.
  4. Update PR description with chosen solution.

Gate: No Phase 3 without a draft PR pushed to remote.


Phase 3: Execute

  1. Set up worktree: scripts/prep-worktree.sh .claude/worktrees/<issue> <branch>, set CARGO_TARGET_DIR=$PWD/target
  2. Scan before coding: repo-native-alignment scan --repo . --full — verify non-zero symbol count before touching any source file
  3. Spawn oh-execute agent with the session file as context
  4. Push commits to PR branch. Tag with [outcome:X] if relevant.

Gate: SALVAGE verdict → stop and surface to user.


Phase 4: Ship

Spawn the ship agent. Do NOT inline ship steps.

Agent(subagent_type="ship", prompt="/ship <PR-number>\n\nWORKTREE: <path>\nCARGO_TARGET_DIR: <path>/target")

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.

  1. 8d ago First seen · 76 lines · 33 tokens per session scan A cf1f4d0723fd

Subscribe to this mod's changes

dev-pipeline is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (4 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 775 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.