agentmods.dev

dogma: Skill for Claude Code

.github/skills/rate-limit-resilience/SKILL.md

rate-limit-resilience is a skill for Claude Code from EndogenAI/dogma. It costs 35 tokens per session (2,632 once invoked), scanned A, original, Apache-2.0.

A workflow for checking provider rate limits before delegating work. Rate limits restrict how many requests or tokens a service allows within a period of time.

In plain words
What is it for?
Use it before orchestration or delegation phases to load a provider policy, check available capacity, limit retries, pause when needed, and record the decision.
Why use it?
It helps prevent token exhaustion and repeated failed requests by applying provider-specific budgets, retry rules, circuit breakers, and audit records.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: mentions AGENTS.md.

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dogma configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/rate_limit_gate.py 50000 delegation \.

not rated 2repo 2mo ago A scan 35 tokens original Apache-2.0
View source ↗ EndogenAI/dogma
Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/skills/rate-limit-resilience/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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 rate-limit-resilience

README.md
[![agentmods](https://agentmods.dev/badge/skills/endogenai/dogma/rate-limit-resilience/github.svg)](https://agentmods.dev/skills/endogenai/dogma/rate-limit-resilience)
Your own site
<a href="https://agentmods.dev/skills/endogenai/dogma/rate-limit-resilience"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/rate-limit-resilience/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rate-limit-resilience

Your own site · 80×15
<a href="https://agentmods.dev/skills/endogenai/dogma/rate-limit-resilience"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/rate-limit-resilience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.02632
Opus 5.5 $0.00014 $0.01053
Sonnet 5.5 $0.00007 $0.00526
Haiku 4.5 $0.00003 $0.00263

Measured 2mo ago against content hash 8e4c9a17651a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rate-limit-resilience scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
.github/skills/rate-limit-resilience/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rate-Limit Resilience — Pre-Delegation Gate Workflow

Beliefs & Context

Governing Axiom (from MANIFESTO.md#3-local-compute-first): Rate-limit constraints are structural constraints on token usage, not optional optimizations. Treating them as a first-class system property (not a post-hoc scaling concern) enables reliable multi-phase sessions without token exhaustion.

Integration Points:

Related Research:

Workflow & Intentions

1. Load Provider Policies

At the start of a delegation, the orchestrator loads provider-specific rate-limit policies:

from rate_limit_config import get_policy

policy = get_policy(provider='claude', operation='delegation')
# Returns: {'sleep_sec': 60, 'retry_limit': 1, 'circuit_breaker_threshold': 3}

Available Providers:

  • claude — Anthropic Claude API (conservative: 60s minimum sleep)
  • gpt-4 — OpenAI GPT-4 (moderate: 30s minimum sleep)
  • gpt-3.5 — OpenAI GPT-3.5 (permissive: 20s minimum sleep)
  • local-localhost — Local inference (no rate limit: 0s sleep)
  • fallback — Unknown providers (conservative fallback)

Available Operations:

  • fetch_source — Source fetching during research
  • delegation — Agent delegation phase
  • phase_boundary — Phase transitions
  • review_gate — Review agent invocations
  • commit — GitHub commits/API calls

2. Pre-Delegation Budget Check

Before delegating a phase, call rate_limit_gate.py:

Read the full file on GitHub · 289 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. 2mo ago First seen · 289 lines · 35 tokens per session scan A 8e4c9a17651a

Subscribe to this mod's changes

rate-limit-resilience is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,632 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI Safetyagentagents-mdaiai-governanceai-harness
Related

rate-limit-resilience compared with skills from other repositories

rate-limit-resilience next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rate-limit-resilienceEndogenAI/dogmaSkill22mo agoApache-2.0A35Claude Code
custom-brand-designKbWen/agentic-osSkill2274d agoMITA23Claude Code, Codex
air-blackbox-sales-agentairblackbox/airblackboxSkill254d agoApache-2.0A248Claude Code, Codex
interpret-resultsairblackbox/airblackboxSkill254d agoApache-2.0A49Claude Code
compliance-scanairblackbox/airblackboxSkill254d agoApache-2.0A51Claude Code
nio-external-scorecore0-io/nioSkill2013d agoApache-2.0A97Claude Code
nio-scancore0-io/nioSkill2013d agoApache-2.0A81Claude Code