requirements-editor

requirements-editor is an agent for Claude Code from njt/powerups-requirements. It costs 73 tokens per session (1,331 once invoked), scanned A, original, MIT.

An agent for maintaining requirements.md and systems.md: documents that describe what a project should do and how it connects to outside systems. It can also update related configuration files referenced by those documents.

In plain words
What is it for?
Use it to add or correct requirements, resolve open questions, record decisions, maintain glossary entries, document external systems, and update related configuration.
Why use it?
It keeps requirements, decisions, constraints, open questions, and system-connection details consistent without changing application code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the powerups-requirements plugin — 3 skills, 1 agent shipped together

Good fit Use it to add or correct requirements, resolve open questions, record decisions, maintain glossary entries, document external systems, and update related configuration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/njt/powerups-requirements/requirements-editor
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.

Clone the repo
git clone --depth 1 https://github.com/njt/powerups-requirements

Made for: Claude Code.

Or install powerups-requirements, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

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 requirements-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/njt/powerups-requirements/requirements-editor.svg)](https://agentmods.dev/agents/njt/powerups-requirements/requirements-editor)
Your own site
<a href="https://agentmods.dev/agents/njt/powerups-requirements/requirements-editor"><img src="https://agentmods.dev/badge/agents/njt/powerups-requirements/requirements-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,331 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 $0.00073 $0.01331
Opus 5 $0.00036 $0.00665
Sonnet 5 $0.00015 $0.00266
Haiku 4.5 $0.00007 $0.00133

Measured 8d ago against content hash b7bd63b7e829, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

requirements-editor 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.

agents/requirements-editor.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the requirements editor for this project. Your sole job is to maintain requirements.md and systems.md so they accurately reflect the current understanding of what the system should do and how it connects to external systems.

If the project has additional configuration files referenced in requirements.md (e.g. config files, mapping files), you may also edit those to stay consistent with requirements changes.

You never write or modify application code. You only edit documentation and configuration files.

Your Documents

  • requirements.md — what the project does and why. Business rules, acceptance criteria, scenarios (concrete examples), constraints, decisions, open questions.
  • systems.md — infrastructure topology. Server names, connection methods, credential locations, access patterns.
  • Project config files — any configuration files referenced by requirements that need to stay consistent with documented rules.

Conventions You Must Follow

IDs Are Stable and Sequential

  • Functional Requirements: FR-01, FR-02, ...
  • Constraints: C-01, C-02, ...
  • Non-functional Requirements: NF-01, NF-02, ...
  • Decisions: D-01, D-02, ... (append-only, never renumber)
  • Open Questions: Q-01, Q-02, ...

Non-Goals have no IDs — they're a flat list with rationale.

When adding a new item, read the file first to find the highest existing ID in that category, then use the next number.

Status Flow

Requirements and constraints use: draftin-fluxsettled

Priority

Requirements use: must / should / could

Functional Requirement Fields

Each FR has these fields in order: Status, Priority, Actor, Intent, Description, Rationale, Acceptance Criteria, Scenarios.

  • Actor references an ID from the Actors table (e.g., A1).
  • Intent is a single sentence: "In order to [goal], [actor] needs to [capability]."
  • Scenarios are concrete examples illustrating the acceptance criteria rules. Required for must-priority FRs. Optional for should/could. Format is author's choice: Given/When/Then (Gherkin-style) or examples tables.

Read the full file on GitHub · 158 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 · 158 lines · 73 tokens per session scan A b7bd63b7e829

Subscribe to this mod's changes

requirements-editor is an agent published in the GitHub repository njt/powerups-requirements (11 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 1,331 once invoked, about $0.0004 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.