agentmods.dev

agent-core

A parent skill for managing an AI agent’s memory, goals, priorities, approvals, safety, tasks, and system health.

In plain words
What is it for?
Use it to choose supporting skills and handle memory, permissions, prompt-injection checks, task tracking, approvals, and system readiness.
Why use it?
It helps keep the agent’s operating decisions organized and applies safety checks across related tasks.

Skill for Claude CodeCodex

10 22d ago A scan 28 tokens original MIT
View the source file CodeInfinity1/Stram
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-core
Any agent
npx skills add CodeInfinity1/Stram --skill agent-core
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 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 $0.00028 $0.00459
Opus 5 $0.00014 $0.00230
Sonnet 5 $0.00006 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 2d ago against content hash bc03da4bfd0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-core 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (secrets-handling/scripts/redact_text.py, system-health-check/scripts/check_readiness.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 53 lines

What it actually says

Agent Core

Purpose

Use this parent skill when a request is about the agent's own operating loop: memory, goals, priorities, approvals, safety, autonomy, task tracking, system state, or capability health.

Hierarchy Reading Rules

  1. Read this parent first to choose the smallest relevant child skill.
  2. Prefer child summaries and Tool Maps before loading full child instructions.
  3. Load a child skill with agent_skill_read when its detailed workflow will change the next action.
  4. Keep safety, approval, and memory instructions active across child workflows.

Tool Map

  • agent-access-control
  • agent-self-assessment
  • agent-self-reflection
  • ambient-room-context
  • approval-gated-external-actions
  • audit-trail-review
  • autonomous-loop-operations
  • bot-loop-protection
  • capability-audit
  • capability-surfaces
  • focus-and-priority-review
  • memory-metabolism
  • persona-evolution
  • prompt-injection-screening
  • secrets-handling
  • session-wrap-up
  • system-health-check
  • task-tracking
  • taskflow
  • wakeup-scheduling

Child Skill Guide

  • Use access, approvals, prompt-injection, bot-loop, and secrets skills for safety boundaries before high-risk or external actions.
  • Use taskflow, task tracking, focus, priorities, wakeups, and autonomous loop skills to plan, continue, or schedule agent work.
  • Use memory, reflection, self-assessment, persona, and session wrap-up skills when the agent should learn, summarize, or improve from work.
  • Use capability audit, capability surfaces, audit trail, ambient context, and system health skills to inspect what the agent can do and whether the environment is ready.

Verification

  • Do not claim durable learning, approval, or scheduling happened unless the relevant child tool or child skill produced evidence.
  • Keep user-visible status honest when an action is prepared, queued, approved, blocked, or completed.
Files

What ships with it

23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 53 lines · 28 tokens per session scan A bc03da4bfd0c

Subscribe to this mod's changes

agent-core is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 28 tokens to every session and 459 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.

Data and AIMemory and contextSecurityai-agentai-agentsai-toolsdesktop-automationdesktop-automation-softwaredesktop-automation-windows
Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

redteam-web-detail-pack

Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.

Netw0rkNoob/VulnClaw · 38 tokens

android-pentest

安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.

Netw0rkNoob/VulnClaw · 32 tokens

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens