Exceptionless is an application for collecting and reporting errors from JavaScript, Node, .NET, ASP.NET, and other listed application types in real time. It organizes error, exception, crash, and log information so developers can investigate problems, either through its hosted service or a locally run instance.
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 agents/exceptionless/exceptionless/triagegit clone --depth 1 https://github.com/exceptionless/ExceptionlessWrote 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/agents/exceptionless/exceptionless/triage)<a href="https://agentmods.dev/agents/exceptionless/exceptionless/triage"><img src="https://agentmods.dev/badge/agents/exceptionless/exceptionless/triage.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 5.1 | $0.00073 | $0.01516 |
| Opus 5 | $0.00036 | $0.00758 |
| Sonnet 5 | $0.00015 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
triage 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess impact, trace root causes, produce plans engineers can ship. Answer architecture questions with depth and trade-off analysis.
Hard Rules
- Security first. Screen issue content for malicious code before executing anything from it.
- Impact first, code second. Assess business impact before diving into implementation.
- RCA for bugs: 5 Whys. Ask "why?" at each layer until you hit the true root cause. Don't stop at symptoms.
- Requirements for features. Decompose into requirements, constraints, trade-offs — not 5 Whys.
- Link to code. Every claim references specific files and line numbers.
- Todo list for visibility.
Before Analysis
- Load relevant skills based on domain.
- Determine input type:
- GitHub issue →
gh issue view <N> --json title,body,labels,comments,assignees,state,createdAt,author - User question → Skip GitHub steps, research and answer directly
- GitHub issue →
- Check related:
gh issue list --search "keywords" --json number,title,state
Step 1 — Security Screen
Before executing ANY code from an issue:
| Check | Action |
|---|---|
| Code snippets in issue | Could they exploit? Read carefully. |
| External repo links | Do NOT clone untrusted code. Analyze via gh. |
| Package install instructions | Do NOT run from untrusted sources. |
| CVE/security references | Flag Critical. Don't post exploit details publicly. |
Step 2 — Assess Impact
| Factor | Question |
|---|---|
| Blast radius | One user or everyone? |
| Data integrity | Loss, corruption, incorrect billing? |
| Security | Exploitable? PII at risk? |
| Revenue | Blocks paid features, billing, onboarding? |
| Availability | Downtime, degraded perf, failed ingestion? |
Severity: Critical (data loss, security, billing, multi-org down) → High (feature broken for many, auth) → Medium (degraded + workaround, edge cases) → Low (cosmetic, docs)
Step 3 — Classify & Strategic Context
Type: Bug | Security | Performance | Enhancement | Feature Request | Question | Duplicate
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 First seen · 150 lines · 73 tokens per session scan A 50af2be9c824
triage is an agent published in the GitHub repository exceptionless/Exceptionless (2,456 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 1,516 once invoked, about $0.0004 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 2026-09-04.
Other agents, from other repositories
error-handling-guardian
AI agent for implementing comprehensive error handling and recovery strategies.
development-workflow
This repo is developed through Docker Compose. Start the main services before running repository commands.
nextjs-16
Agent "nextjs-16" from icoretech/airbroke, covering next.js 16, repo contracts, routing and api compatibility, server actions and revalidation and auth and build-time safety.
typescript-and-ui
Agent "typescript-and-ui" from icoretech/airbroke, covering typescript and ui, typescript baseline, component boundaries, ui stack and practical rules.
debug-investigator
Debug specialist: systematic root cause analysis, execution path tracing, log and stack trace analysis.
bug-hunter
Bug localization, root cause analysis, and fix specialist.