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/rimio-ai/rimz/adapter_codexgit clone --depth 1 https://github.com/rimio-ai/rimzWrote 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/rimio-ai/rimz/adapter_codex)<a href="https://agentmods.dev/agents/rimio-ai/rimz/adapter_codex"><img src="https://agentmods.dev/badge/agents/rimio-ai/rimz/adapter_codex.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 | $0.08918 |
| Opus 5 | $0.00000 | $0.04459 |
| Sonnet 5 | $0.00000 | $0.01784 |
| Haiku 4.5 | $0.00000 | $0.00892 |
Grade B, and why
adapter_codex scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Install.** Installed ask hooks use the short lifecycle timeout because they record the waiting observation and return neutral. Install writes inline `[[hooks.Event]]` tables in `~/.codex/config.toml` with the same `--e How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex adapter
Read model.md for the provider-neutral agent model and adapter.md for the integration layer every adapter implements. Accounts, balances, and spend are in providers.md; the raw upstream protocol is in codex-reference.md.
This doc is the single home for everything Codex-specific: the native-event mapping, the daemon-routed launch quirks, the rollout and app-server context read-path, and the account, balance, and spend surfaces.
Hooks and lifecycle
Native event or derived surface → internal mapping; the upstream events, payloads, and decision schema are in codex-reference.md.
| Native event / surface | Channel | decode_hook → LifecycleSignal |
Normalized fields |
|---|---|---|---|
SessionStart |
lifecycle | Registered; source = "compact" maps to CompactionEnded { auto: None } |
model, effort, root lineage, compact predecessor |
UserPromptSubmit |
lifecycle | TurnStarted |
root prompt, or child progress when agent_id is distinct |
SubagentStart |
lifecycle | SubagentStarted |
child id plus rollout nickname/path/role/model/context |
SubagentStop |
lifecycle | SubagentStopped { errored } |
child rollout error marker decides the verdict |
Stop |
lifecycle / awaiting-user | AwaitingInput { PlanApproval } when the resting rollout carries a same-turn Plan item; otherwise TurnEnded { errored, parked_on_background: false } |
plan detail or clear task; refresh context/tokens; merge rollout markers |
PermissionRequest |
awaiting-user | AwaitingInput { Permission } → waiting |
— |
PreToolUse: request_user_input |
awaiting-user | AwaitingInput { Question } → waiting |
user question |
PostToolUse |
lifecycle | ToolUsed { mutates, edits } for every observed tool completion |
edits for apply_patch; non-mutating completions use proof-of-work persistence, including answered asks |
PreToolUse (other observed tools) |
lifecycle | ToolUsed { mutates: false, edits: false } as proof-of-work only |
persisted when it reconciles a resting row, clears waiting, or closes a compaction bracket |
PreCompact |
lifecycle | Compacting |
stamps the head |
PostCompact |
lifecycle | CompactionEnded with known trigger |
safely redundant as a close; carries the auto/manual trigger bit |
| pane liveness + rollup reaper | derived | durable end stamp and runtime hiding for the hooks matrix ended row |
gap: no SessionEnd hook; hidden after liveness convergence, not at session exit |
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.
- yesterday Changed d83b0bbc061a
- 5d ago First seen · 141 lines · 0 tokens per session scan B 854f00c01da5
adapter_codex is an agent published in the GitHub repository rimio-ai/rimz (23 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,918 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
memory-proposal-collector
Reference documentation (NOT a dispatchable agent) for the coordinator-direct AUQ rendering flow at session-end Phase 3.6.3. The coordinator collects proposals from .orchestrator/metrics/proposals.jsonl via collectProposals() and renders the multiSelect AUQ in batches of 4. Approved proposals flow to learnings.jsonl…
test-writer
Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. Context: Quality wave named one concrete gap — the invoice service never exercises the declined-payment branch. user: "The invoice…
ux-evaluator
Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…
qa-strategist
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, error paths, and integration gaps not caught by happy-path tests. Context: Impl-Core shipped a new auth flow with 6 unit tests. user: "Check the test coverage gaps." assistant: "I'll dispatch qa-strategist to…
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…
dialectic-deriver
Use this agent when reasoning over top-N learnings + last-K sessions + existing peer cards to derive updates to USER.md / AGENT.md. Called via /evolve --dialectic mode by the evolve skill. Reads inputs, writes one fenced diff block per peer-card target. Read-only by contract — never writes files. Cheap-by-default …