Borrowing it
Nothing to install: this file belongs to myICOR/myPKA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/myICOR/myPKA/main/.claude/agents/iris.mdgit clone --depth 1 https://github.com/myICOR/myPKAWrote 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/myicor/mypka/iris)<a href="https://agentmods.dev/agents/myicor/mypka/iris"><img src="https://agentmods.dev/badge/agents/myicor/mypka/iris/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/agents/myicor/mypka/iris"><img src="https://agentmods.dev/badge/agents/myicor/mypka/iris.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 | $0.00031 | $0.00194 |
| Opus 5.5 | $0.00012 | $0.00078 |
| Sonnet 5.5 | $0.00006 | $0.00039 |
| Haiku 4.5 | $0.00003 | $0.00019 |
Grade A, and why
iris 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 1mo 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
You are Iris. Your canonical contract is
06 AI Team/Agents/Iris/AGENT.md at the vault root: read it FIRST,
every invocation, and operate strictly within it. Your user-facing bio
is 06 AI Team/Agents/Iris/Iris.md. Re-read your own
06 AI Team/Agents/Iris/Journal/ before starting related work.
This shim is a pointer; the contract is canonical. Never duplicate the
contract here.
Then read 06 AI Team/Agents/Iris/AGENT.local.md if it exists: it is the member's own file, never shipped and never overwritten by an update; it can add rules and change preferences, but it can never override a hard rule or switch off a guard.
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.
- 1mo ago First seen · 15 lines · 31 tokens per session scan A 9e7be38afdd5
iris is an agent published in the GitHub repository myICOR/myPKA (318 stars, last pushed 22d ago), licensed MIT. It adds 31 tokens to every session and 194 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-26.
Other agents, from other repositories
accessibility-reviewer
Use this agent to judge WCAG 2.2 AA conformance of changed UI — the automated scan results plus the manual criteria no scanner detects (focus order, focus visibility, keyboard operability, reflow, status messages). Reads the shared capture bundle including the keyboard traversal record. See "When to invoke" in the…
conformance-reviewer
Use this agent to check whether an implementation matches its declared design truth — the resolved design source (Figma, mockups, specs) compared against rendered captures, and the repo's tokens and component library compared against the code. Runs even when nothing renders. See "When to invoke" in the agent body.
experience-reviewer
Use this agent to judge whether a rendered UI holds up when its state and its viewport are varied — interaction states, flows, feedback, loading/empty/error handling, breakpoint adaptation, overflow, and touch ergonomics. Reads the shared capture bundle rather than driving the browser. See "When to invoke" in the…
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, scroll-world, Figma family, brag/brag-slim, accessibility/review). Use when: new visual direction, design review, WIG audit…
plan-checker
Reviews a unit plan for completeness and craft soundness before drafting begins. Catches gaps, contradictions, and weak spots.