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/amadeus-dlc/amadeus/error-classificationnpx skills add amadeus-dlc/amadeus --skill error-classificationgit clone --depth 1 https://github.com/amadeus-dlc/amadeusWhat 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 | $0.00066 | $0.00367 |
| Opus 5 | $0.00033 | $0.00183 |
| Sonnet 5 | $0.00013 | $0.00073 |
| Haiku 4.5 | $0.00007 | $0.00037 |
Grade A, and why
error-classification 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.
What it actually says
Error Classification
Classify abnormal states before designing their handling. Different words imply different interventions.
Working Vocabulary
-
Error: a human or system mistake in reasoning, input, configuration, or operation.
-
Defect: a flaw in an artifact such as code, requirements, tests, or documentation.
-
Bug: an informal report or label for a defect, fault, or failure; clarify which precise category is meant before choosing a response.
-
Fault: an incorrect internal state or latent condition that can cause failure.
-
Failure: externally observable deviation from expected service.
-
Incident: an operational event requiring response.
-
Exception: a language/runtime control mechanism or signal, not a domain classification by itself; classify the condition it represents.
Workflow
-
Describe what was observed and by whom.
-
Separate external failure from internal fault and underlying defect.
-
Identify whether the condition is recoverable, retryable, user-correctable, or fatal.
-
Choose handling: validation error, typed domain error, exception, retry, circuit breaker, alert, or defect fix.
Detailed Reference
For non-trivial implementation, review, or refactoring work, read references/details.md before giving final guidance. It contains the detailed rules, examples, smells, and migration notes that do not belong in the short invocation body.
Output
Return the classification chain, handling strategy, tests to add, and terms the team should use consistently.
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.
- 2d ago First seen · 44 lines · 66 tokens per session scan A 868640d9e388
error-classification is a skill published in the GitHub repository amadeus-dlc/amadeus (8 stars, last pushed 12d ago), licensed Apache-2.0. It adds 66 tokens to every session and 367 once invoked, about $0.0003 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
trellis-plan-review
Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies repository claims and path:line citations against code, traces every acceptance-criterion clause to a requirement and design mechanism, rechecks arithmetic and…
anti-monolith-guard
Prevent mixed-responsibility modules and uncontrolled file growth.
agent-factory
Evidence-based gate for creating a new skill or agent profile.
code-hygiene-refactor
Select a bounded, behavior-preserving code-hygiene batch.
git-conventional-commits
Prepare scoped conventional commits, tags, and release messages.
self-improvement
Improve an existing skill or agent from evidence while preserving scope.