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-agent-profile-managementgit 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-agent-profile-management)<a href="https://agentmods.dev/skills/chronoaiproject/nyxid/aevatar-agent-profile-management"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-agent-profile-management/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-agent-profile-management"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-agent-profile-management.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 Tool Misuse · line 58 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Privilege Escalation · line 185 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.
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 | $0.00125 | $0.03714 |
| Opus 5 | $0.00063 | $0.01857 |
| Sonnet 5 | $0.00025 | $0.00743 |
| Haiku 4.5 | $0.00013 | $0.00371 |
Grade A, and why
aevatar-agent-profile-management 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 11d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aevatar Agent Profile management
An Agent Profile answers "who is this agent, and what may it do?" — display name, purpose, instructions, an ordered set of exact Ornn skill bindings, and the maximum tool authority any turn under that profile may hold.
It is an independent resource surface. It is not another phase of the studio lifecycle:
build & operate : scope → team → member (workflow|script|gagent) → service → schedule
Agent Profile : ownerHandle/profileSlug → opaque profileId → draft → published snapshot
profileId, workflowId, memberId, publishedServiceId, and a conversation actor id are
five different identities. No prefix, string match, or lifecycle story converts one into
another. Creating or publishing a Profile creates no workflow, member, team, service,
schedule, or conversation binding.
Step 0 — Detect the capability. Do this before anything else.
The Profile contract is a deployment-gated capability. It ships in the Aevatar codebase but a given deployment may not expose it. A 404 on a profile resource is not a deployment probe — probe the surface itself, and stop honestly when it is absent.
In-session tool mode. Use the Profile path only if the exact tool agent_profiles is
present in your current tool list. Never infer it from another aevatar_* tool, from Ornn
access, from the system prompt, or from this skill being loaded.
Client REST mode. Read the live document and require the complete route family:
nyxid proxy request aevatar "api/openapi.json" \
| jq -r '.paths|keys[]|select(test("agent-profiles"))'
POST /api/scopes/{scopeId}/agent-profiles
GET /api/scopes/{scopeId}/agent-profiles/{profileSlug}
PUT /api/scopes/{scopeId}/agent-profiles/{profileSlug}/draft
PUT /api/scopes/{scopeId}/agent-profiles/{profileSlug}/draft/skills/{bindingId}
DELETE /api/scopes/{scopeId}/agent-profiles/{profileSlug}/draft/skills/{bindingId}
POST /api/scopes/{scopeId}/agent-profiles/{profileSlug}:validate
POST /api/scopes/{scopeId}/agent-profiles/{profileSlug}:publish
GET /api/agent-profiles/{ownerHandle}/{profileSlug}
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.
- 11d ago First seen · 283 lines · 125 tokens per session scan A b9ab803aac73
aevatar-agent-profile-management is a skill published in the GitHub repository ChronoAIProject/NyxID (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 3,714 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…
authoring-decorators
Use when the user wants to write a new prompt decorator - either a personal one for their repo or a contribution back to the upstream catalogue. Walks through the JSON schema, the extensions/ convention, how to verify a new decorator end-to-end through the hook, and how to diagnose failures using debug logging and…