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.
npx agentmods add skills/marcusrbrown/systematic/slfgnpx skills add marcusrbrown/systematic --skill slfggit clone --depth 1 https://github.com/marcusrbrown/systematicWhat 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 | $0.00013 | $0.00463 |
| Opus 5 | $0.00006 | $0.00231 |
| Sonnet 5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
slfg 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 3d 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.
What it actually says
Swarm-enabled LFG. Run these steps in order, parallelizing where indicated. Do not stop between steps — complete every step through to the end.
Sequential Phase
- Optional: If the
ralph-loopskill is available, run/ralph-loop:ralph-loop "finish all slash commands" --completion-promise "DONE". If not available or it fails, skip and continue to step 2 immediately. /ce:plan $ARGUMENTS- Conditionally run
/systematic:deepen-plan- Run the
deepen-planworkflow only if the plan isStandardorDeep, touches a high-risk area (auth, security, payments, migrations, external APIs, significant rollout concerns), or still has obvious confidence gaps in decisions, sequencing, system-wide impact, risks, or verification - If you run the
deepen-planworkflow, confirm the plan was deepened or explicitly judged sufficiently grounded before moving on - If you skip it, note why and continue to step 4
- Run the
/ce:work— Use swarm mode: Make a Task list and launch an army of agent swarm subagents to build the plan
Parallel Phase
After work completes, launch steps 5 and 6 as parallel swarm agents (both only need code to be written):
/ce:review mode:report-only— spawn as background Task agent/systematic:test-browser— spawn as background Task agent
Wait for both to complete before continuing.
Autofix Phase
/ce:review mode:autofix— run sequentially after the parallel phase so it can safely mutate the checkout, applysafe_autofixes, and emit residual todos for step 8
Finalize Phase
/systematic:todos(resolve) — resolve findings, compound on learnings, clean up completed todos- Output
<promise>DONE</promise>when work is complete
Start with step 1 now.
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.
- 3d ago First seen · 40 lines · 13 tokens per session scan A 3c799a746cf2
slfg is a skill published in the GitHub repository marcusrbrown/systematic (24 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 463 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.
Other skills, from other repositories
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
hud
Configure HUD display options (layout, presets, display elements).
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
plan-protocol
Guidelines for creating and managing implementation plans with citations.
plan-review
Criteria for reviewing implementation plans against quality standards.