security-profile

A command for creating or refreshing a project-specific defensive security profile based on a shared security baseline.

In plain words
What is it for?
Use it to generate or update files under .opencode/skills/security-profile/ for a project’s stack, environments, security owners, response deadlines, and release-blocking rules.
Why use it?
It turns general security guidance into project-specific settings, responsibilities, risk thresholds, and verification commands.

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/mazumba/opencode-dockerized/security-profile
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 972 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 $0.00010 $0.00972
Opus 5 $0.00005 $0.00486
Sonnet 5 $0.00002 $0.00194
Haiku 4.5 $0.00001 $0.00097

Measured yesterday against content hash 31468a38b485, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-profile 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 yesterday.

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.

.opencode/config/commands/security-profile.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create or update a project-local security-profile skill using security-core as the baseline.

Command usage:

  • /security-profile init
  • /security-profile refresh
  • /security-profile init <project-name>
  • /security-profile refresh <project-name>

Default mode is init when no mode is provided.

Spec

Inputs

  • mode: init or refresh
  • project_name (optional): override inferred project name

Outputs

Under .opencode/skills/security-profile/ ensure these files exist:

  • SKILL.md
  • GOTCHAS.md
  • HISTORY.md
  • config.json
  • assets/.gitkeep
  • scripts/.gitkeep

config.json shape

{
  "project": "<string>",
  "stack": ["<string>"],
  "environments": ["<environment-name>"],
  "severity_sla_days": {
    "critical": "<days>",
    "high": "<days>",
    "medium": "<days>",
    "low": "<days>",
    "informational": "<days>"
  },
  "risk_threshold": {
    "block_release_at_or_above": "high"
  },
  "ci_verify_commands": ["<command>"],
  "ownership": {
    "security": "<team-or-individual>",
    "default_service_owner": "<team-or-individual>"
  },
  "defensive_only": true
}

Defensive policy

  • This command and resulting skill are defensive-only.
  • Never add exploit-building, payload development, bypass instructions, or offensive operation guidance.
  • If asked for offensive detail, redirect to detection, mitigation, patching, validation, and disclosure handling.

What to do

  1. Read .opencode/skills/security-core/SKILL.md first.
  2. Parse $ARGUMENTS into mode and optional project_name.
  3. Infer project metadata from repo files when possible:
    • project name from root directory or manifest
    • stack from common files (composer.json, package.json, pyproject.toml, go.mod, Dockerfile, *.tf)
    • CI verify commands from existing project tooling
    • environments from CI/deploy config when available, otherwise use conservative defaults and ask
  4. Ensure .opencode/skills/security-profile/ exists with required files.
  5. Write or update files:

Read the full file on GitHub · 134 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. yesterday First seen · 134 lines · 10 tokens per session scan A 31468a38b485

Subscribe to this mod's changes

security-profile is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 972 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.