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/kreek/consult/error-handlingnpx skills add kreek/consult --skill error-handlinggit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/error-handling)<a href="https://agentmods.dev/skills/kreek/consult/error-handling"><img src="https://agentmods.dev/badge/skills/kreek/consult/error-handling.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00685 |
| Opus 5 | $0.00012 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
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 today.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Handling
Iron Law
ERRORS CARRY CONTEXT. NEVER CATCH WITHOUT HANDLING OR RE-RAISING.
When to Use
- Designing or reviewing typed errors, Result/Either flows, domain error boundaries, wrapping, retries, remote-call failures, panics, user-facing errors, or swallowed failures.
When NOT to Use
- Security-specific failure shape; pair with
security. - REST status codes or public API error schema; use
api. - Error visibility in production; pair with
observability.
Rules
- Failure is part of the function contract. Expected failures are typed
(named exception classes, discriminated unions, structured
Resultvariants), never bare strings or anonymous generic errors. - Catch only where you can decide: recover, translate, retry, or terminate. Every catch does one of those or re-raises with context, preserving the original cause.
- Translate at boundaries. Domain, infrastructure, API, CLI, and UI errors do not leak across a boundary unchanged.
- Remote calls declare timeout, retry, idempotency, and dependency-failure behavior (circuit breaker, bulkhead, load shedding, or fail fast) together, before the caller is written. Retries apply only to idempotent transient failures, in one layer, with a capped budget and jittered backoff. Two retrying layers multiply load on a failing dependency.
- User-facing errors are actionable and expose no stack traces, SQL, file paths, hostnames, secrets, or auth-enumeration clues. Diagnostic detail stays reachable by correlation ID.
- Panics and assertions are for impossible states and process boundaries, not routine control flow.
- Every public operation that can fail has at least one failure-path test.
Tripwires
| Trigger | Do this instead | False alarm |
|---|---|---|
| "Log and continue is fine" | Decide: recover, translate, retry, or terminate. | Best-effort telemetry with an explicit drop policy. |
| "This can't fail in practice" | Declare the failure-capable contract and test a representative failure. | The state is impossible by type or value construction. |
| "Swallow at the boundary" | Translate for the caller and preserve the cause for diagnostics. | A security boundary deliberately hides details while logging a correlation ID. |
| "We'll add remote-call protection later" | Define timeout, retry budget, idempotency guard, and dependency-failure behavior now. | Local in-memory call with no blocking I/O. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -36 lines b27a29dcc848
- 4d ago First seen · 103 lines · 23 tokens per session scan A 37110cf5d368
error-handling is a skill published in the GitHub repository kreek/consult (1 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 685 once invoked, about $0.0001 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.