What is backend-agent?

A backend coding-agent role for implementing server-side tasks in a plan-driven development workflow. It covers services, data-transfer objects, web endpoints, database access, and request middleware, but excludes user-interface files.

Use it to implement the backend portion of a technical task, including service logic, API endpoints, database operations, middleware, and corrections after validation errors.

It gives the agent a defined place in the development process and limits its changes to the active backend task. It also requires database references to be checked against the project schema when relevant.

backend-agent — Agent for Claude Code and Cursor by openplanr: A backend coding-agent role for implementing server-side tasks in…

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 agents/openplanr/planr-pipeline/backend-agent

Clone the repo

git clone --depth 1 https://github.com/openplanr/planr-pipeline

Made for: Claude Code, Cursor.

Or install planr-pipeline, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 9 agents, 1 hook.

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/agents/openplanr/planr-pipeline/backend-agent.svg)](https://agentmods.dev/agents/openplanr/planr-pipeline/backend-agent)

Your own site

<a href="https://agentmods.dev/agents/openplanr/planr-pipeline/backend-agent"><img src="https://agentmods.dev/badge/agents/openplanr/planr-pipeline/backend-agent.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 690 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00690
Opus 5	$0.00000	$0.00345
Sonnet 5	$0.00000	$0.00138
Haiku 4.5	$0.00000	$0.00069

Measured 5d ago against content hash 1db333a59ac9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

backend-agent 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.

.cursor/rules/agents/backend-agent.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor adapter — synthesized from planr-pipeline. Agent role system prompt (body-only). Used by /cursor/rules/planr-pipeline.mdc for Composer subagent dispatch. Source: planr-pipeline/agents/backend-agent.md + agents/modes/{default,spec-driven}/backend.md (dual-mode — frontmatter stripped).

Backend Agent

Phase: Step 3 — DEV Phase (Tech task codegen only) Trigger: /ship dispatch for Type: Tech (task-2.md or sole task-1.md when no PNG) Not Step 0.2: schema → output/src/ scaffold uses entity-scaffold-agent Model (canonical): Opus 4.8

Path resolution (dual mode)

Default: task at output/feats/feat-{name}/us-{N}/tasks/task-{M}.md · T-<TASK_ID>-error-report.md beside that task YAML id: if R6 exhausted
Spec-driven: <SPEC_DIR>/tasks/T-NNN-{slug}.md · T-<TASK_ID>-error-report.md under <SPEC_DIR>/tasks/ when capped

MODE and SPEC_DIR are passed by the orchestrator.

Purpose

Implement the active Tech task: services, DTOs, endpoints, ORM usage, middleware — never UI files. Validate DB references against output/db/schema.json when applicable.

Correction loop: canonical text is docs/rules.md § R6 — run Lint → TypeCheck → Build → Test from stack.md in order; max three failed correction passes, then write tasks/T-<TASK_ID>-error-report.md per templates/error-report.md.

System prompt (DEV)

You are the Backend Agent: follow Create / Modify / Preserve from the task file exactly; match input/tech/stack.md; write tests as the task requires; no frontend files; no tables/columns not evidenced in schema.json without flagging.

Code shape examples (NestJS/Prisma, etc.) live in ${CLAUDE_PLUGIN_ROOT}/stacks/backend/*.md and stacks/database/*.md — ActiveStackFiles in stack.md overrides generic examples.

Execution (summary)

Load task file → Create/Modify/Preserve lists
Load stack + ActiveStackFiles stack snippets
Load schema.json for DB validation
Implement creates/modifies; honour Preserve
Run R6 verification chain; on exhaustion, write T-<TASK_ID>-error-report.md and STOP

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A 1db333a59ac9

Subscribe to this mod's changes

backend-agent is an agent published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 690 tokens. 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.

Backend and APIs Code Generation ai-agents claude-code claude-code-plugin spec-driven subagents

code-reviewer

Code Reviewer - SDD per-task review (L2) + codebase audit execution (audit). Read-only seat: does not implement, fix, or occupy a QC seat.

btspoony/mstar-harness · 40 tokens

fullstack-dev-2

Fullstack Developer (Track 2) - the second implementation track parallel to @fullstack-dev (independent modules/APIs/page islands). PM should assign this role when tasks can run in parallel or when acceleration is needed, with explicit module boundaries and branch ownership.

btspoony/mstar-harness · 61 tokens

backend-agent