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/undertone0809/rudder/identity-configgit clone --depth 1 https://github.com/Undertone0809/rudderWrote 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/undertone0809/rudder/identity-config)<a href="https://agentmods.dev/agents/undertone0809/rudder/identity-config"><img src="https://agentmods.dev/badge/agents/undertone0809/rudder/identity-config.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 | $0.00000 | $0.05079 |
| Opus 5 | $0.00000 | $0.02540 |
| Sonnet 5 | $0.00000 | $0.01016 |
| Haiku 4.5 | $0.00000 | $0.00508 |
Grade A, and why
identity-config 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Identity And Config
AGENT.IDENTITY.CONFIG.001
Why:
- Agents are durable team members, not throwaway runtime processes. Their role, capabilities, runtime, skills, budget, and permissions define what work Rudder may safely route to them.
Product model:
- An agent belongs to one organization.
- Agent identity includes name, role, title, capabilities, status, runtime type/config, desired skills, budget, and permission/config state.
- The board's New Agent form derives the role from the organization's current
agent list: the first agent is submitted with role
ceo, and later agents are submitted with rolegeneral. This form does not expose a role picker; other explicit creation or hire callers still provide a server-validated role. - Agent avatar identity uses the existing
agents.iconfield. Supported persisted generated references are deterministic Oreooreo:<shape>:<palette>:<uuid>values and DiceBear Notionists values; uploadedasset:<uuid>references remain supported. - New direct-created and hired agents default to a server-generated Oreo
reference when
iconis omitted or a legacy named icon is supplied. The persisted UUID is Oreo's stable variant identity across refreshes, restarts, and every shared avatar rendering surface. - Existing agents are not migrated. Persisted Oreo, DiceBear, uploaded-image, legacy named-icon, and missing-icon display behavior remains intact.
- Agent Detail exposes a compact Oreo/DiceBear avatar picker. Oreo provides its six shapes, 40 palettes, and style-scoped Random; DiceBear retains Notionists Random and six background presets; image upload is shared across both tabs.
- Pending approval, paused, terminated, or revoked-access states constrain whether the agent can be woken or configured.
- A board-originated hire is direct even when the organization enables
requireBoardApprovalForNewAgents, because the initiating board actor already holds the approval authority. An agent-originated hire under that policy is created aspending_approvalwith one governed approval request. - Config changes are operator-visible product changes when they alter runtime, instruction, skill, budget, or permission behavior.
- External local runtime configuration is a connection identity, not a provider credential dump. It stores the runtime type, normalized transport/endpoint, local ownership mode, and a Rudder secret reference; plaintext OpenClaw device keys, Hermes bearer keys, and provider session IDs do not belong in general Agent config JSON.
- For provider authentication, local-adapter onboarding collects the runtime choice and model name, along with any runtime-owned execution options exposed by that adapter. It does not collect provider API keys or create provider secret bindings as part of the basic Agent config flow. Provider authentication remains configuration owned by the selected agent runtime; Rudder may show runtime-owned setup guidance and probe the environment, while generic environment or secret-reference controls remain an advanced runtime configuration surface.
- V1 local ownership modes are
rudder_managed_localandattach_existing_local. Managed mode owns only the recorded process identity and start epoch and binds it to the resolved workspace. Each process identity and start epoch has exactly one lifecycle owner; a second Agent may share a reachable endpoint only in attach mode and cannot restart or stop the managed process. Attach mode records that Rudder does not own lifecycle and is eligible only for the workspace binding that the provider/process can prove. - An external endpoint/credential tuple is a single-organization trust domain. A secret reference already bound to one organization cannot be attached to a different organization, and provider session mappings are scoped by organization, Agent, and workstream rather than stored as reusable Agent identity fields.
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 Changed · +13 lines d10178cfff2d
- 5d ago First seen · 401 lines · 0 tokens per session scan A 12e631b87086
identity-config is an agent published in the GitHub repository Undertone0809/rudder (288 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,079 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.