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.
npx skills add hajekim/agentic-design-patterns-extension --skill exception-handlinggit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extensionWrote 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.
[](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/exception-handling)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/exception-handling"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/exception-handling/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.
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/exception-handling"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/exception-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00383 | $0.03670 |
| Opus 5 | $0.00192 | $0.01835 |
| Sonnet 5 | $0.00077 | $0.00734 |
| Haiku 4.5 | $0.00038 | $0.00367 |
Grade A, and why
exception-handling 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get(url, timeout=10) This is a copy
100% identical to exception-handling — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exception Handling Pattern
Overview
The Exception Handling Pattern enables agents to detect, respond to, and recover from errors, failures, and unexpected conditions without crashing or producing incorrect outputs. Robust agents treat exceptions as information — they classify the failure, choose an appropriate recovery strategy, and continue operating or escalate gracefully.
Core Principle: Expect failure as a first-class event — design recovery paths before you need them.
When This Skill Applies
Activate this pattern when:
- Agents call external APIs, databases, or services that can fail or time out
- Tool calls may return malformed, unexpected, or empty responses
- Agent reasoning can produce invalid actions (bad parameters, out-of-scope requests)
- Long-running tasks must survive transient failures without full restart
- Resource exhaustion (token limits, rate limits, quotas) is possible
- Partial failures in multi-step pipelines must not silently corrupt outputs
Rule of thumb: If an agent can fail (and it can), it needs exception handling — every external call, every tool invocation, every LLM response that requires a specific format.
Exception Classification
By Cause
| Exception Type | Examples | Recovery |
|---|---|---|
| Transient | Network timeout, rate limit | Retry with backoff |
| Input Error | Invalid parameters, bad format | Validate, re-prompt |
| Tool Failure | API down, auth expired | Fallback tool or skip |
| Logic Error | Contradictory goals, impossible task | Escalate or abort |
| Resource Exhaustion | Token limit, quota exceeded | Summarize, paginate, escalate |
By Severity
- Recoverable: Agent can self-correct and continue
- Degradable: Agent continues with reduced capability
- Fatal: Agent must stop and notify the user/operator
DEFINE → PLAN → ACTION Workflow
DEFINE
Map the failure landscape:
- What external dependencies does the agent have? (APIs, tools, LLMs)
- What can go wrong at each dependency? (Network, auth, rate limit, format)
- What is the acceptable degraded behavior for each failure?
- When should the agent retry vs. escalate vs. abort?
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.
- 8d ago First seen · 429 lines · 383 tokens per session scan A b2434ea82a42
exception-handling is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 383 tokens to every session and 3,670 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to exception-handling, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
vault-lint
Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps. Triggers on "lint vault", "vault health", "check vault", "stale notes", "vault audit", "vault quality", or "check conventions".
canary-watch
Post-deploy monitoring and canary health verification.
discord-troubleshooting
Troubleshoots and resolves gemini-discord bot connection, gateway issues (e.g. fatal disconnects 4014, 4004), and port conflicts. Ensures the bot gets online and operational by running loops to verify success.
debug-assistant
Systematic debugging assistant that helps identify and fix bugs through structured analysis, hypothesis testing, and root cause identification. Use when facing errors, unexpected behavior, or mysterious bugs.
quick-fix
Apply a minimal, targeted fix to a specific bug or issue. Focused on speed and precision - locate the problem, make the smallest correct change, and verify. Not a planning workflow; use for small fixes, patches, and hotfixes.
openqa-log-analyzer
A specialized skill for analyzing openQA logs — triage failures, measure command timing, detect infrastructure lag, extract command output, and compare runs across multiple log files.