sdlc-task

A rule for running all seven stages of the software development life cycle (SDLC) without human approval gates. It produces code, tests, documentation, and reports from architecture through security auditing.

In plain words
What is it for?
Use it to run a development task through architecture, security planning, implementation, code review, quality checks, and security auditing, with a consolidated report at the end.
Why use it?
It lets the workflow continue from one stage to the next automatically and revisit the architecture when later findings change the work.

Cursor rule for Cursor

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 rules/redhat-vmeperf/agent-tasks-template/sdlc-task
Clone the repo
git clone --depth 1 https://github.com/redhat-vmeperf/agent-tasks-template

Made for: Cursor.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 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 $0.00027 $0.00331
Opus 5 $0.00014 $0.00166
Sonnet 5 $0.00005 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 2d ago against content hash 005c46c8794c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-task 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 2d 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/sdlc-task.mdc · 32 lines

What it actually says

SDLC Task (Autonomous)

This rule runs the 7-gate SDLC pipeline without human approval gates. Read .agents/skills/sdlc-task/PIPELINE.md for the full pipeline process definition.

Invocation

  • "Run SDLC task for [task]" — Run the full autonomous pipeline

If the user does not provide a task description, ask them to describe the task.

SDLC Task Context

This pipeline produces the same artifacts as the gated SDLC — code, tests, inline documentation, and all gate reports — but without blocking on human approval at any gate.

  • All 7 roles execute in sequence (Architect through Security Auditor)
  • All gate artifacts are produced (ADR, SAR, Sprint Brief, Implementation Report, Code Review, Quality Report, Security Audit)
  • Self-correction: discoveries that change architecture, scope, or security posture loop back to Gate 1 (max 2 cycles)
  • Finding mitigation is driven by the invoker's directions — findings within scope are mitigated, findings outside scope are flagged
  • Audit trail entries are marked UNGATED
  • Output: Consolidated Report summarizing all gates and re-evaluation cycles

Security

  • Security roles still execute their full analysis.
  • No interaction with any service or system may reduce the security posture of data passing through the process (REQ-5).
  • External context files must pass a security review before loading (REQ-6).
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. 2d ago First seen · 32 lines · 27 tokens per session scan A 005c46c8794c

Subscribe to this mod's changes

sdlc-task is a cursor rule published in the GitHub repository redhat-vmeperf/agent-tasks-template (3 stars, last pushed 4mo ago), licensed Unlicense. It adds 27 tokens to every session and 331 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.