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 skills add ChronoAIProject/NyxID --skill aevatar-triagegit clone --depth 1 https://github.com/ChronoAIProject/NyxIDWrote 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/chronoaiproject/nyxid/aevatar-triage)<a href="https://agentmods.dev/skills/chronoaiproject/nyxid/aevatar-triage"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chronoaiproject/nyxid/aevatar-triage"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 265 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 296 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00119 | $0.09884 |
| Opus 5 | $0.00060 | $0.04942 |
| Sonnet 5 | $0.00024 | $0.01977 |
| Haiku 4.5 | $0.00012 | $0.00988 |
Grade A, and why
aevatar-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 9d 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 — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aevatar triage — find the layer, read the code, then report or guide
Something broke (or looks wrong) while using Aevatar. Your job is three honest moves:
(1) attribute the failure to the right layer — Aevatar / NyxID / Ornn — by tracing the
request path; (2) read the real code of that layer until you have a code-grounded root
cause (cite path:line) that matches what's actually deployed; (3) branch: if it is a
genuine platform defect (behavior that violates the layer's own published contract), draft
and — only on explicit user confirmation — file a GitHub issue to the owning repo; if it is a
usage / config mistake, give the user an authoritative, code-grounded explanation and the
correct usage. This is the after-it-breaks counterpart to aevatar-feasibility-advisor (which
answers "is it possible, before building").
You make real calls and read real code — no guessing, no fabricated root cause, no auto-filing.
The three layers (and their repos — all public)
| Layer | Repo (stack) | Owns | Canonical symptoms |
|---|---|---|---|
| Aevatar | aevatarAI/aevatar (C#/.NET) |
agent runtime + tool execution, workflow engine, channels, CQRS/projection + readmodels, control-plane REST, scheduler validation | workflow validate / draft-run / run failures, member-team-service binding stuck (async never succeeded), the aevatar side of a channel bot, stale readmodel / observatory, scheduled run that stops firing, control-plane 4xx/5xx |
| NyxID | ChronoAIProject/NyxID (Rust) |
credential-broker gateway: proxy + credential injection, OAuth/OIDC/PKCE/MFA, connector vault, NAT relay + SSH, approvals, MCP-from-OpenAPI | nyxid_proxy 401/403, "credential not found", connector/slug missing, OAuth/token/MFA failures, grant revoked (invalid_grant), inbound relay not delivering, approval stuck |
| Ornn | ChronoAIProject/Ornn (TS/Node) |
skills-as-a-service registry: skill search/pull/upload/generate, skillsets, sandbox | skill not found / search / pull / upload fails, use_skill cannot find a skill, skillset integrity, generate (SSE) errors |
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.
- 9d ago First seen · 483 lines · 119 tokens per session scan A aa4380c5e0f3
aevatar-triage is a skill published in the GitHub repository ChronoAIProject/NyxID (36 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 9,884 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.