agents-tier-system

A reference system for organizing agent rules and skills into three tiers based on when they apply. It also documents which rules and skills should be paired and provides a checklist for writing them.

In plain words
What is it for?
Use it when creating or reviewing agent configuration, choosing between Tier 1, 2, and 3, checking rule and skill pairings, or auditing the cost of attached instructions.
Why use it?
It helps maintainers decide what should always load, apply only to certain files, or be discovered only when relevant. This limits unnecessary instructions and prevents broad rules from piling up.

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/stainless-code/codemap/agents-tier-system
Any agent
npx skills add stainless-code/codemap --skill agents-tier-system
Clone the repo
git clone --depth 1 https://github.com/stainless-code/codemap

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 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 $0.00049 $0.01226
Opus 5 $0.00024 $0.00613
Sonnet 5 $0.00010 $0.00245
Haiku 4.5 $0.00005 $0.00123

Measured 2d ago against content hash 77ab81e73d24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-tier-system 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.

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.

.agents/skills/agents-tier-system/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.agents/ tier system — full reference

Always-on priming: .agents/rules/agents-tier-system.md. Entry points: .agents/README.md (hub), AGENTS.md (cross-tool stub), agents-first-convention, writing-agents-config.

Discover on disk (do not maintain partial catalogs here)

Tier How to list
Tier 1 Frontmatter audit in agents-tier-system rule — budget set there
Tier 2 ls .agents/rules/*.md + globs: in frontmatter
Tier 3 alwaysApply: false, no globs: — intent via description
Skills ls .agents/skills — runtime discovery via descriptions

Pairing examples in this repo: consumer-surfaces (Tier 1, always-on); docs-governance (Tier 2 globs) ↔ docs-governance + docs-lifecycle-sweep; architecture-primingimprove-codebase-architecture + audit-pr-architecture; agents-tier-system rule + skill; authoring-discipline rule + PROSE.md; verify-after-each-step rule + skill; codemap (skill-only); harden-pr (skill-only).

Caution: avoid stacking broad globs without thin priming bodies.

Authoring guidelines

Adding a new rule

  1. Decide the tier before writing.
  2. Tier 1 needs justification — every turn? If file/intent scoped, demote to Tier 2 or Tier 3.
  3. Tier 2 globs — broadest meaningful scope; pair with skill when applicable.
  4. Layout per agents-first-convention — rules: source + .mdc symlink; skills: .agents/ only.

Read the full file on GitHub · 67 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. 2d ago First seen · 67 lines · 49 tokens per session scan A 77ab81e73d24

Subscribe to this mod's changes

agents-tier-system is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,226 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.

Related

Other skills, from other repositories

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

self-repair-pipeline

Runs the full entry point self-repair pipeline. Detects entry points in Ariadne packages or external codebases, triages false positives via sub-agents, plans fixes for each issue group with competing proposals and multi-angle review, and creates backlog tasks.

CRJFisher/ariadne · 57 tokens

m1nd-guardian

Use when continuing, coordinating, reviewing, or handing off the M1ND-10 program; protecting its candidate tree; advancing G0-G10; freezing or releasing a candidate; activating autonomy; or when the user asks an agent to act as M1ND guardian. Enforces one-active-front execution, proof-state separation, same-candidate…

maxkle1nz/m1nd · 99 tokens

ctxo-understand

Use at the START of any code task (fix, extend, refactor, understand) before reading source files, to orient with ctxo and avoid going in the wrong direction.

alperhankendi/Ctxo · 41 tokens

agent-system-maintainer

Use this skill when modifying AI agents, skills, prompts, commands, hooks, instructions, MCP configuration, or platform-specific AI customization files.

configflux/weld · 33 tokens

reposkein-graph-rag

Navigates the local RepoSkein Code Property Graph to understand repository architecture. Use whenever modifying code, tracing dependencies, assessing change impact, or summarizing functions in a repo containing .reposkein/.

reposkein/reposkein · 46 tokens