sop-activate

sop-activate is a command for coding agents from SSBun/csl-agent-kit. It costs 20 tokens per session (974 once invoked), scanned A, original, MIT.

A command for activating a built-in standard operating procedure as a Claude Code rule.

In plain words
What is it for?
It helps list available procedures and activate one globally or for a project, with conditional or other loading modes.
Why use it?
It makes selected project guidance load automatically in Claude Code instead of requiring the instructions to be remembered each time.

Command

Part of the csl plugin — 33 skills, 2 commands, 5 agents, 10 hooks shipped together

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/ssbun/csl-agent-kit/sop-activate
Clone the repo
git clone --depth 1 https://github.com/SSBun/csl-agent-kit

Or install csl, the plugin that ships this one along with the rest of its 33 skills, 2 commands, 5 agents, 10 hooks.

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 sop-activate

README.md
[![agentmods](https://agentmods.dev/badge/commands/ssbun/csl-agent-kit/sop-activate.svg)](https://agentmods.dev/commands/ssbun/csl-agent-kit/sop-activate)
Your own site
<a href="https://agentmods.dev/commands/ssbun/csl-agent-kit/sop-activate"><img src="https://agentmods.dev/badge/commands/ssbun/csl-agent-kit/sop-activate.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 974 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 $0.00020 $0.00974
Opus 5 $0.00010 $0.00487
Sonnet 5 $0.00004 $0.00195
Haiku 4.5 $0.00002 $0.00097

Measured 3d ago against content hash 0308d892c76a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sop-activate 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.

commands/sop-activate.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate a built-in SOP so it loads as a native Claude Code rule. Claude Code only — Cursor users should use the agent-sops skill's Activate SOP workflow; this command does not write Cursor rules. Codex has no rules directory.

Step 1: List Available SOPs

List all built-in SOPs:

ls "${CLAUDE_PLUGIN_ROOT}/skills/meta/agent-sops/sops/" 2>/dev/null

Also check for custom SOPs already activated:

ls ~/.claude/rules/sop-*.md 2>/dev/null
ls .claude/rules/sop-*.md 2>/dev/null

Present the list to the user using AskUserQuestion.

Step 2: Ask Which SOP to Activate

Use AskUserQuestion:

  • Question: "Which SOP to activate?"
  • Header: "Select SOP"
  • Options: each built-in SOP file (drop .md extension as label)

If no SOPs exist, tell the user and stop.

Step 3: Ask Scope and Activation Mode

Use AskUserQuestion with two questions:

Question 1 — Scope:

  • Header: "Scope"
  • Options:
    • "Global (~/.claude/rules/)" — applies to all projects
    • "Project (.claude/rules/)" — applies to this project only

Question 2 — Activation mode:

  • Header: "Activation"
  • Options:
    • "Conditional — load only when matching files are edited" (recommended)
    • "Always — load in every conversation"

Step 4: Determine Globs (Conditional Only)

If conditional mode chosen, determine the glob pattern for the SOP.

Option A — SOP already declares globs in frontmatter: use those.

Option B — Infer from SOP name/content: ask the user to confirm or provide globs. Common mappings:

SOP Suggested glob
swift-* ["**/*.swift"]
python-* ["**/*.py"]
golang-* / go-* ["**/*.go"]
typescript-* / ts-* ["**/*.ts", "**/*.tsx"]
kotlin-* ["**/*.kt", "**/*.kts"]
deploy-* ["**/*.yml", "**/*.yaml", "**/Dockerfile"]

Use AskUserQuestion to confirm the glob or let the user type a custom one.

Step 5: Write Activated Rule

Read the source SOP:

cat "${CLAUDE_PLUGIN_ROOT}/skills/meta/agent-sops/sops/{selected}.md"

Read the full file on GitHub · 138 lines

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. 3d ago First seen · 138 lines · 20 tokens per session scan A 0308d892c76a

Subscribe to this mod's changes

sop-activate is a command published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 974 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.