agentmods.dev

stl-init

stl-init is a command for coding agents from SummerSec/SumSec-Skills. It costs 12 tokens per session (261 once invoked), scanned A, original, Apache-2.0.

A setup command for Semantic-Linter, a project tool that maintains rules about code wording and meaning. It creates a project rules file and adds a managed rules section to AGENTS.md or CLAUDE.md.

In plain words
What is it for?
Use it when first enabling Semantic-Linter in a project, or when generating its initial local configuration.
Why use it?
It gives the coding agent project-specific semantic rules to follow and establishes which rules file takes priority.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the semantic-linter plugin — 4 skills, 3 commands shipped together

not rated 8 20d ago A scan 12 tokens original Apache-2.0
View the source file SummerSec/SumSec-Skills
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/summersec/sumsec-skills/stl-init
Clone the repo
git clone --depth 1 https://github.com/SummerSec/SumSec-Skills

Or install semantic-linter, the plugin that ships this one along with the rest of its 4 skills, 3 commands.

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 stl-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/summersec/sumsec-skills/stl-init.svg)](https://agentmods.dev/commands/summersec/sumsec-skills/stl-init)
Your own site
<a href="https://agentmods.dev/commands/summersec/sumsec-skills/stl-init"><img src="https://agentmods.dev/badge/commands/summersec/sumsec-skills/stl-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 261 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 $0.00012 $0.00261
Opus 5 $0.00006 $0.00130
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 4d ago against content hash 19cc10ee368f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stl-init 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 4d 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.

semantic-linter/commands/stl-init.md · 36 lines

What it actually says

Semantic-Linter Init

Use this command to bootstrap project-local semantic rules.

Steps

  1. Treat the current working directory as the target project.
  2. Locate scripts/build-rules.js from one of these paths:
    • ${CODEX_PLUGIN_ROOT}/scripts/build-rules.js
    • ${CLAUDE_PLUGIN_ROOT}/scripts/build-rules.js
    • ./scripts/build-rules.js
    • $HOME/.claude/plugins/semantic-linter/scripts/build-rules.js
  3. Run:
node "<SCRIPT>" --existing "$(pwd)"
  1. Tell the user which files were written:
    • semantic-rules.md
    • managed rules block in AGENTS.md and/or CLAUDE.md
  2. Explain the runtime behavior:
    • Claude uses hooks plus the managed rules block.
    • Codex uses the managed rules block in AGENTS.md.
    • the default mode is guarded
    • the project rules file is preferred over the plugin fallback

Notes

  • Do not hand-write the managed rules block.
  • Re-run /stl-rules after lexicon or wording policy changes.
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. 4d ago First seen · 36 lines · 12 tokens per session scan A 19cc10ee368f

Subscribe to this mod's changes

stl-init is a command published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 20d ago), licensed Apache-2.0. It adds 12 tokens to every session and 261 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.

dsh-plugin
Related

Other commands, from other repositories

ov

Show OpenViking memory plugin status — server, identity, last injection / recall, toggles.

volcengine/OpenViking · 19 tokens

manps

Inspect project health through mancode.

whitelonng/dshcode · 7 tokens

riskreview

The user invoked the /riskreview facade command from the risk-review-pipeline pack.

inclusionAI/Avernet · 11 tokens

delegate

Delegate a task in the background / 在后台委派大型任务.

cpj-dev/dsh-plugin-cc · 13 tokens

approval

The user invoked the /approval facade command from the approval-node-pipeline pack.

inclusionAI/Avernet · 9 tokens

aw

The user invoked the /approval-web facade command from the approval-node-pipeline pack.

inclusionAI/Avernet · 11 tokens