slrj

A command for carrying out a full software-engineering workflow with multiple agents working in parallel. A swarm is a group of agents assigned different parts of the same job.

In plain words
What is it for?
Use it to plan and build a feature, run parallel code review and browser testing, resolve findings, and record the completed work.
Why use it?
It provides an ordered path from planning through implementation, review, browser testing, issue resolution, and a final walkthrough. This keeps a large change moving through its required checks.

Command

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 commands/aegntic/compound-engineering/slfg
Clone the repo
git clone --depth 1 https://github.com/aegntic/compound-engineering
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 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 $0.00014 $0.00288
Opus 5 $0.00007 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 485007027d36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slrj 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.

commands/slfg.md · 34 lines

What it actually says

Swarm-enabled LRJ. Run these steps in order, parallelizing where indicated.

Sequential Phase

  1. /workflows:plan $ARGUMENTS
  2. /compound-engineering:deepen-plan
  3. /workflows:workUse swarm mode: Make a Task list and launch an army of agent swarm subagents to build the plan. This is the default Ralph-driven execution path and should emit red, green, and post-refactor green evidence unless the plan declares an explicit exception.

Parallel Phase

After work completes, launch steps 4 and 5 as parallel swarm agents (both only need code to be written):

  1. /workflows:review — spawn as background Task agent
  2. /compound-engineering:test-browser — spawn as background Task agent

Wait for both to complete before continuing.

Finalize Phase

  1. /compound-engineering:resolve_todo_parallel — resolve any findings from the review
  2. /compound-engineering:feature-video — record the final walkthrough and add to PR
  3. Output <promise>DONE</promise> when video is in PR

Start with step 1 now.

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 · 34 lines · 14 tokens per session scan A 485007027d36

Subscribe to this mod's changes

slrj is a command published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 288 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.