agentmods.dev

requirements

requirements is a skill for Claude Code from scolladon/craft. It costs 28 tokens per session (334 once invoked), scanned A, original, MIT.

A requirements-writing workflow that turns a product brief or specification into a requirements document and lists decisions that may need recording.

In plain words
What is it for?
Use it to create requirements documents, check them against the brief, and identify decisions for later architecture discussions.
Why use it?
It provides a written statement of what should be built before design and implementation begin.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the craft plugin — 20 skills, 4 commands, 9 agents, 1 hook shipped together

not rated 2 18d ago A scan 28 tokens original MIT
View the source file scolladon/craft
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add scolladon/craft
Claude Code
/plugin install craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 20 skills, 4 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.

agentmods badge for requirements

README.md
[![agentmods](https://agentmods.dev/badge/skills/scolladon/craft/requirements.svg)](https://agentmods.dev/skills/scolladon/craft/requirements)
Your own site
<a href="https://agentmods.dev/skills/scolladon/craft/requirements"><img src="https://agentmods.dev/badge/skills/scolladon/craft/requirements.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 334 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00334
Opus 5 $0.00014 $0.00167
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured 6d ago against content hash 7df55ea0bae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

requirements 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 6d 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.

skills/requirements/SKILL.md · 30 lines

What it actually says

craft:requirements

Preamble (always runs — non-overridable)

  1. manifest-lint.sh must pass (skip if the orchestrator already ran it this turn); read manifest. Standalone: scope defaults to the current branch vs the default branch; establish global-context preconditions against the current checkout root.
  2. Probe: requirements docs directory (paths.requirements, else docs/requirements/, create if absent); repo's own requirements template, else "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/templates/requirements.md".

Procedure (default body — a manifest override: replaces everything below)

  1. Spawn craft:requirements-writer with: the resolved brief (and any source PRD/spec path); the absolute working directory; the output path <requirements-dir>/<slug>.md; the template; the commit message docs(requirements): <slug>; the manifest's global + requirements-phase context: files verbatim.
  2. When it returns: READ THE DOC (not the agent's exploration). Sanity-check it against the brief; verify the commit exists and the decision-candidates were returned.
  3. The design phase consumes the produced requirements artifact; record the outcome in the run record.
  4. Dead agent → respawn fresh from the brief + whatever the doc already contains.
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. 6d ago First seen · 30 lines · 28 tokens per session scan A 7df55ea0bae4

Subscribe to this mod's changes

requirements is a skill published in the GitHub repository scolladon/craft (2 stars, last pushed 18d ago), licensed MIT. It adds 28 tokens to every session and 334 once invoked, about $0.0001 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.

PlanningWriting and docsagentic-codingai-agentsclaude-codeclaude-code-plugindeveloper-tools
Related

Other skills, from other repositories

horizon

Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.

Master0fFate/parallax-claudecode · 22 tokens

check-in

Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.

Master0fFate/parallax-claudecode · 17 tokens

debug

Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.

Master0fFate/parallax-claudecode · 18 tokens

hyperplan

Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.

Master0fFate/parallax-claudecode · 22 tokens

status

Report the current Claude session's Parallax gate, retries, verification, and trace status.

Master0fFate/parallax-claudecode · 20 tokens

parallax

Compatibility entry point for the Parallax workflow when Claude resolves it as a plugin skill.

Master0fFate/parallax-claudecode · 20 tokens