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 berkcangumusisik/agent-hub --skill load-profilegit clone --depth 1 https://github.com/berkcangumusisik/agent-hubWrote 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/berkcangumusisik/agent-hub/load-profile)<a href="https://agentmods.dev/skills/berkcangumusisik/agent-hub/load-profile"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/agent-hub/load-profile/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/berkcangumusisik/agent-hub/load-profile"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/agent-hub/load-profile.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.00293 |
| Opus 5 | $0.00028 | $0.00147 |
| Sonnet 5 | $0.00011 | $0.00059 |
| Haiku 4.5 | $0.00006 | $0.00029 |
Grade A, and why
load-profile 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 10d 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.
What it actually says
load-profile
Orient to the current project before doing work.
Steps
- Read
.claude/agent-hub/profile.yml. If it does not exist, tell the user there's no profile and suggest theagent-hub-initskill (or/onboard). Stop. - Read
.claude/CLAUDE.mdif present for extra context and conventions. - Read any recorded decisions under
.claude/agent-hub/decisions/(the team's memory). Honor accepted ADRs — never silently contradict one. - Summarize back, briefly:
- Project name, type, and stack (language / framework / database).
- The real commands (install/dev/test/lint/build).
- The active team members and what they cover.
- Any
conventions,doNotrules, and key decisions on record.
- Hold this context for the session. When delegating, only invoke specialists listed in
team.active, and pass them the relevant profile facts.
This is the bridge that makes the same super-team behave differently from one project to the next.
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.
- 10d ago First seen · 23 lines · 57 tokens per session scan A 957de5c54e1d
load-profile is a skill published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 293 once invoked, about $0.0003 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
omnigent-knowledge
Deep reference on Omnigent config format, executor types, skill/tool structure, and conventions. Load when you need to look up how the platform works.
build-omnigent
Patterns and templates for generating valid Omnigent agent directories. Load when ready to create files.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
detect-framework
Detect Python agent frameworks from code imports and map them to Omnigent executor types. Load when the user has existing agent code to integrate.
api-docs
Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself. Use when the user asks for API reference, to document a module, or to write usage docs for a public interface.
migration-guide
Turn a breaking change (an API rename, removed flag, changed default, or moved module) into concrete upgrade steps with before/after examples. Use when the user asks how to migrate, upgrade, or adapt to a breaking change.