GroundRules: Skill for Claude Code

.agents/archive/v3/skill_tool-call-resilience/SKILL.md

tool-call-resilience is a skill for Claude Code, Codex from chama-x/GroundRules. It costs 31 tokens per session (285 once invoked), scanned A, original, MIT.

Guidance for making an AI agent's calls to tools and external services handle failures safely. It covers retries, waiting between attempts, stopping repeated failures, rate limits, and timeouts.

In plain words
What is it for?
Use it when building agents that call APIs, databases, or other network services. It helps add backoff, circuit breakers, rate-limit handling, timeouts, and fallback behavior.
Why use it?
It reduces failures caused by temporary network problems, overloaded services, or API limits. It also helps prevent an agent from waiting forever or repeatedly calling a broken service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is chama-x/GroundRules's own configuration. It tells Claude Code and Codex how to work on GroundRules 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 GroundRules configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chama-x/GroundRules. 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/chama-x/GroundRules/master/.agents/archive/v3/skill_tool-call-resilience/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chama-x/GroundRules

Made for: Claude Code, Codex.

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 tool-call-resilience

README.md
[![agentmods](https://agentmods.dev/badge/skills/chama-x/groundrules/skill_tool-call-resilience.svg)](https://agentmods.dev/skills/chama-x/groundrules/skill_tool-call-resilience)
Your own site
<a href="https://agentmods.dev/skills/chama-x/groundrules/skill_tool-call-resilience"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/skill_tool-call-resilience.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.00285
Opus 5 $0.00015 $0.00143
Sonnet 5 $0.00006 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 7d ago against content hash 706984ec4328, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tool-call-resilience 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 7d 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/archive/v3/skill_tool-call-resilience/SKILL.md · 26 lines

What it actually says

Agent Tool-Call Resilience Engineer

You are an expert in resilience engineering for LLM agent tool calls and distributed systems.

1. Retry with Exponential Backoff and Jitter

  • Never use flat retry loops.
  • Implement exponential backoff (delay = base * 2^attempt).
  • Add jitter to prevent thundering herd problems (e.g., delay = delay * random(0.5, 1.5)).

2. Circuit Breakers

  • If an external API fails repeatedly (e.g., 5 times in a row), open the circuit breaker to fail fast.
  • Wait for a reset timeout before transitioning to a "half-open" state to test if the service is back online.

3. Rate-Limit Handling (HTTP 429)

  • Always respect Retry-After headers if present in API responses.
  • Implement client-side token buckets or leaky buckets if calling APIs with known strict rate limits.

4. Timeout Management

  • Set aggressive timeouts on all network calls. Never block indefinitely.
  • Implement fallback mechanisms when a timeout occurs (e.g., returning cached data or gracefully degrading).
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. 7d ago First seen · 26 lines · 31 tokens per session scan A 706984ec4328

Subscribe to this mod's changes

tool-call-resilience is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 285 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.