What is sruja-plan-feature?

A command that creates a file-level implementation plan for one task in a Sruja workspace. The plan covers affected files, task order, validation commands, and risks.

Use it to plan which files to change, sequence the work, and define checks such as Rust builds, tests, or Sruja linting.

It turns an agreed feature or fix into concrete coding steps without silently expanding the product’s scope.

sruja-plan-feature — Command for Claude Code and Cursor by sruja-ai

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/sruja-ai/sruja

Made for: Claude Code, Cursor.

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/commands/sruja-ai/sruja/sruja-plan-feature/github.svg)](https://agentmods.dev/commands/sruja-ai/sruja/sruja-plan-feature)

Your own site

<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-plan-feature"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-plan-feature/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-plan-feature"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-plan-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 339 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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.00339
Opus 5	$0.00005	$0.00169
Sonnet 5	$0.00002	$0.00068
Haiku 4.5	$0.00001	$0.00034

Measured 9d ago against content hash c88d8ff59725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sruja-plan-feature 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 9d 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/commands/sruja-plan-feature.md · 28 lines

What it actually says

You are planning a single task in the Sruja workspace. Obey AGENTS.md and two-layer planning: this command is task layer only (files, order, validation)—not full product scope.

Inputs the user should provide (ask if missing):

Issue / goal statement (or link)
Optional: target file or crate

Steps:

Confirm scope layer is already settled (what ships, what is out of scope). If unclear, stop and ask—do not invent product scope.
Inspect only the code paths needed: search, then read relevant modules. Prefer sruja focus / MCP over bulk reads.
Produce one plan artifact with this structure (markdown, save where the user wants—often PR branch plan.md or issue comment):
- Summary — One paragraph.
- User-visible behavior — Bullets.
- Files to create or change — Path list with one-line rationale each.
- Task order — Numbered steps (dependencies first).
- Validation — Exact commands: at minimum just check (or make check) for Rust; add crate-scoped tests if they said so. For .sruja, include sruja lint <file>.
- Risks / unknowns — What could invalidate the plan.
Ask the user to review and freeze the plan before implementation.

Do not start large refactors in this step unless the user explicitly asked for code in the same turn.

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.

9d ago First seen · 28 lines · 11 tokens per session scan A c88d8ff59725

Subscribe to this mod's changes

sruja-plan-feature is a command published in the GitHub repository sruja-ai/sruja (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 339 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 2026-08-30.

Planning agent-loop agent-skills ai architecture developer-tools rust-lang

sruja-plan-feature

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

arrange-workspace-flow-technical-context

plan

xray

check

review-drift

plan-feature