agent-access-control

A set of rules for deciding who an AI agent may respond to and which actions it may take in different channels. It covers users, groups, strangers, messages, and permission-sensitive actions.

In plain words
What is it for?
Use it when configuring channel access, allowlists, group chats, unknown senders, bot protection, approvals, and other permission checks.
Why use it?
It prevents the agent from acting for an unauthorized person or in an untrusted conversation. It also supports drafting or asking for approval when identity or permission is unclear.

Skill for Claude CodeCodex

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 skills/codeinfinity1/stram/agent-access-control
Any agent
npx skills add CodeInfinity1/Stram --skill agent-access-control
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 391 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 $0.00031 $0.00391
Opus 5 $0.00015 $0.00196
Sonnet 5 $0.00006 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured yesterday against content hash 188b4a892b6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-access-control 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.

skills/agent-core/agent-access-control/SKILL.md · 66 lines

What it actually says

Agent Access Control

Purpose

Ensure the assistant responds and acts only for authorized people and contexts. Access control covers channel identity, groups, strangers, and high-risk actions.

When To Use

Use for channel onboarding, group chats, unknown senders, shared rooms, bot messages, external requests, and permission-sensitive tools.

Inputs And Evidence

  • Sender ID, channel ID, conversation type, allowlists, pairing state, and requested action.
  • Channel manifest and setup status.

Tool Map

  • channel_manifest
  • channel_setup_status
  • channel_doctor
  • ambient-room-context
  • bot-loop-protection
  • message-approval-policy

Workflow

  1. Identify actor, channel, and conversation context.
  2. Check allowlist/pairing/group policy.
  3. Classify action risk and external visibility.
  4. Let model-led cognition decide response posture within policy.
  5. Suppress or draft rather than act when identity is uncertain.
  6. Record setup gaps or policy needs.

Native Implementation Boundaries

  • Use Stram channel policy and approval tools.
  • Do not import external reference agent-access-control code.
  • Do not make semantic access decisions with keyword matching.

Safety And Approval

  • Unknown users get limited or no action.
  • High-risk tools need approval even for trusted users.
  • Group contexts require stricter visible-reply policy.

Verification

  • Channel manifest/status proves policy support.
  • Prepared/suppressed outcomes should have reasons.
  • Send claims require native send status.

Failure Modes

  • Treating display names as identity proof.
  • Giving group members DM-level access.
  • Ignoring bot-loop signals.

References

  • Shortlist item: agent-access-control.
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 · 66 lines · 31 tokens per session scan A 188b4a892b6c

Subscribe to this mod's changes

agent-access-control is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 31 tokens to every session and 391 once invoked, about $0.0002 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.