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 commands/aneja5/forge-skills/errorsgit clone --depth 1 https://github.com/aneja5/forge-skillsWhat 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 | $0.00018 | $0.00156 |
| Opus 5 | $0.00009 | $0.00078 |
| Sonnet 5 | $0.00004 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00016 |
Grade A, and why
errors 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 yesterday.
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
Invoke the forge-skills:error-handling-and-resilience skill.
Inventory failure modes per component (network, validation, business rule, dependency, race). Classify each as transient (retry with backoff), permanent (escalate), or user-correctable (catalog message). Assign handling pattern per class — timeouts on every external call, max attempts on every retry, deadlines, idempotency keys. Write error taxonomy with named error types, HTTP codes, circuit breaker thresholds. Define logging + alerting per class. Document compensation for irreversible flows.
After writing: "Error handling written to .forge/error-handling.md. Pair with /observe for the dashboards."
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.
- yesterday First seen · 14 lines · 18 tokens per session scan A 821d59048c18
errors is a command published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 156 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 commands, from other repositories
index
Command "index" from cesarandreslopez/tauri-agent-tools, covering command reference, command summary, categories, visual capture and dom inspection.
snapshot
Capture screenshot + DOM tree + page state + storage in one shot.
console-monitor
Monitor console output (log/warn/error/info/debug) in real-time.
eval
Evaluate a JavaScript expression in the Tauri app's webview.
list-windows
List all visible windows, marking Tauri apps.
storage
Inspect localStorage, sessionStorage, and cookies from the Tauri webview. One-shot read — no writes.