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-automationgit 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-automation)<a href="https://agentmods.dev/skills/chronoaiproject/nyxid/aevatar-automation"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-automation/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-automation"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/aevatar-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 100 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.
- high Privilege Escalation · line 124 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 58 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.
- medium Excessive Agency · line 151 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 | $0.00161 | $0.03832 |
| Opus 5 | $0.00081 | $0.01916 |
| Sonnet 5 | $0.00032 | $0.00766 |
| Haiku 4.5 | $0.00016 | $0.00383 |
Grade A, and why
aevatar-automation 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scheduled_agent_creator (scheduled Ornn skill agents)
Use scheduled_agent_creator to create a new caller-owned scheduled automation agent from an Ornn skill reference, or to create a single delayed reminder.
This tool is for an independent scheduled Ornn skill agent or a one-shot reminder. It is NOT an alias for Studio Team member automation. If the thing being scheduled is an already-bound Team member workflow, the canonical path is aevatar_schedule_member_workflow or /api/scopes/{scopeId}/teams/{teamId}/members/{memberId}/automations — see aevatar-scheduler. Do not route a Team member here, and do not route an independent skill agent to generic /api/schedules.
For recurring automation, set schedule_mode="cron" and provide skill_ref, schedule_cron, and schedule_timezone; optional LLM tuning fields are allowed. If the loaded skill body will call connected NyxID services through nyxid_proxy beyond Ornn and the Lark outbound channel, declare them with the typed requirement contract:
required_nyx_services[] = { user_service_id, service_slug_snapshot }
The exact user_service_id is the authorization; the slug snapshot is an integrity/display value and can never substitute for it. nyx_user_service_id identifies the exact outbound provider where applicable. The older required_service_slugs contract has been removed — do not recommend it, and never infer a UserService ID from a slug, a vendor name, or a catalog service ID (a connected UserService ID and a catalog service ID are different identifiers and are not interchangeable).
If the scheduled agent needs deterministic fire-date fields, its execution prompt may use the same
fire-time Chat template as other schedules: {{@schedule.run_date}}, run_year, run_month,
days_until_month_end, fire_at_utc, and timezone. The prompt must then be valid JSON and each
placeholder must be inside a JSON string value. The values come from the authoritative logical fire
and configured IANA timezone; catch-up keeps the original occurrence and run-now uses the manual
instant. Unknown placeholders or invalid JSON fail closed. A manual run is not cron-rearm proof.
For one-shot delayed reminders such as "remind me in 10 minutes" or "later today tell me ...", set schedule_mode="one_shot" and provide exactly one of delay_seconds or run_at_utc, plus one_shot_message. Prefer delay_seconds when the user gave a relative delay. Do not use code_execute with sleep, timers, polling loops, or long-running scripts for delayed one-shot requests; durable delivery must go through scheduled_agent_creator. Do not publish an Ornn skill just to send a one-shot natural-language reminder unless the user explicitly asks for reusable automation or the reminder requires a real skill workflow.
Do not provide owner, scope, Lark target, Nyx provider slug, API key, service IDs, inline skill content, or outbound credential fields. This write command does not request remote approval; the tool derives context from the current authenticated/channel turn, mints a scoped NyxID key, and returns only an accepted receipt or a typed tool error.
skill_ref must be unversioned for now. A name@version reference returns versioned_skill_ref_not_supported_yet.
The scheduled agent's credential is a dedicated Agent Key
A scheduled_agent_creator agent does not run on a replayed user bearer, and it does not
run on a fire-time broker token. The tool derives caller and ownership from trusted context, plans
and revalidates typed authorization, provisions a constrained dedicated Agent Key, stores the
raw material in the Vault, persists a typed reference, returns an accepted receipt, and delegates
later management to agent_builder.
Secret custody. Raw key material is written only to ISecretVault. Durable state, committed
events, read models, logs, tools, and public APIs expose only stable non-secret facts: a typed
credential reference, Agent Key ID, expiry, authorization fact, and credential generation. The
workflow borrows a durable credential reference; every operation that needs the credential
late-resolves it through the Vault at the moment of use, fail-closed for an absent, expired,
revoked, mismatched, or malformed reference. Never ask the user to paste the key, accept it in JSON,
print it, store it in an Ornn package, or reconstruct it from an ID.
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 · 202 lines · 161 tokens per session scan A 8d9f5e2603c7
aevatar-automation is a skill published in the GitHub repository ChronoAIProject/NyxID (36 stars, last pushed today), licensed Apache-2.0. It adds 161 tokens to every session and 3,832 once invoked, about $0.0008 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
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.