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 agentmods add skills/andr-ca/agentharness/error-handlingnpx skills add andr-ca/agentharness --skill error-handlinggit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00036 | $0.01390 |
| Opus 5 | $0.00018 | $0.00695 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
error-handling 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Handling & Recovery
Structured approaches to errors, recovery, and observability. Never silently hide errors.
Core Patterns
1. Explicit Errors (Always)
Return errors as values or raise them; never ignore them.
# ✅ Good: Explicit handling
try:
user = parse_user_data(raw)
except json.JSONDecodeError as e:
# Never log the raw payload — it can carry passwords/PII. Log a
# bounded, redaction-safe summary instead.
logger.error("Invalid user JSON", extra={"error": str(e), "payload_length": len(raw)})
return None
# ❌ Bad: Silent failure
try:
parse_user_data(raw)
except:
pass # User data silently ignored
2. Error Wrapping (Across Boundaries)
Add context as errors propagate—original error + where + why.
# ✅ Python: Preserve cause
try:
return repository.find(user_id)
except DatabaseError as e:
raise UserNotFoundError(f"find user {user_id}") from e
# ✅ Go: Wrap with context
user, err := repo.Find(userID)
if err != nil {
return nil, fmt.Errorf("find user %s: %w", userID, err)
}
3. Error Classification
Decide recovery strategy based on error type.
def classify_error(error):
if isinstance(error, (ConnectionError, TimeoutError)):
return "transient" # Retry
elif isinstance(error, (ValueError, KeyError)):
return "validation" # Reject, don't retry
else:
return "unknown"
# Transient → retry with backoff
# Validation → log and fail
# Fatal → panic
4. Retry with Backoff (for Transient Errors)
Retry flaky operations; don't retry permanent failures.
import time
def retry(func, max_attempts=3, backoff_base=2):
"""Retry with exponential backoff."""
for attempt in range(max_attempts):
try:
return func()
except (ConnectionError, TimeoutError) as e:
if attempt < max_attempts - 1:
wait_time = backoff_base ** attempt
logger.warning(f"Retry {attempt + 1}/{max_attempts}, waiting {wait_time}s")
time.sleep(wait_time)
else:
raise
except (ValueError, KeyError):
raise # Don't retry validation errors
# Usage
user = retry(lambda: fetch_user(user_id), max_attempts=3)
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.
- 2d ago First seen · 202 lines · 36 tokens per session scan A a492eb34bbdf
error-handling is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,390 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.
Other skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
doca-compress
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…