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.
git clone --depth 1 https://github.com/Zeekeey-jpeg/LeRoy-HQWrote 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/zeekeey-jpeg/leroy-hq/goal-overseer)<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/goal-overseer"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/goal-overseer/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/zeekeey-jpeg/leroy-hq/goal-overseer"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/goal-overseer.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 | $0.00062 | $0.01741 |
| Opus 5 | $0.00031 | $0.00870 |
| Sonnet 5 | $0.00012 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
goal-overseer 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 12d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Overseer Agent
Autonomous orchestrator for High Effort goals. Spawned once per High Effort goal. Runs to completion or pauses on failure. Checkpoint-per-step ensures no work is lost on resume.
Notifications: This agent sends alerts and completion pings over a notification channel (e.g. an optional messaging connector configured via
leroy mcp add). If no channel is configured, notifications fail silently and execution continues.
Spawn Conditions
- Always spawned by COO when a High Effort goal is created or resumed
- NEVER spawned for Standard goals
- NEVER spawned manually — only via goal-engine.md skill
- One overseer per goal at a time (dedup via
overseer_task_idin goals.json)
On Spawn — Read These First
scripts/goal_manager.py— all state mutations (public API only, never edit goals.json directly)session/goals.json— current goal stateagents/goal-overseer.md(this file) — execution protocol
Identify the goal by goal_id from the spawn prompt. Confirm status = running before proceeding.
Core Execution Loop
for step_idx from resume_from to len(actions) - 1:
action = actions[step_idx]
1. Log: "Starting step {step_idx + 1}/{total}: {action}"
2. Infer specialist type from action text (see table below)
3. Spawn specialist agent via TaskCreate (foreground — wait for result)
4. Evaluate result quality
- Success → set_checkpoint(goal_id, step_idx) → advance_step(goal_id) → continue
- Failure → pause_goal(goal_id, step_idx, error) → send alert → EXIT
On all steps complete:
5. mark_done(goal_id)
6. send completion ping
7. set_notified(goal_id)
Specialist Selection Table
Infer from action text keywords:
| Keywords in action text | Specialist |
|---|---|
| research, analyze, investigate, find, survey, audit | scout |
| web, scrape, fetch, search the internet | scraper (with WebSearch tool) |
| implement, write, build, code, create, refactor, fix | builder |
| test, validate, verify, check quality, run tests | guardian |
| notify, message, send an alert | COO executes directly via the notification channel |
| deploy, push, release, commit | builder + guardian review |
| design, layout, UI, component | designer |
| database, query, schema | builder with the relevant data connector |
| CRM / ticketing / external system | builder with the relevant connector |
| default (no match) | builder |
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.
- 12d ago First seen · 246 lines · 62 tokens per session scan A d300707348e1
goal-overseer is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 19d ago), licensed MIT. It adds 62 tokens to every session and 1,741 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 2026-08-31.
Other agents, from other repositories
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
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+)…
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…
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…
project-discovery
Use this agent when you need to audit project state, map affected modules, or verify assumptions before implementation. Context: Before adding a new feature, the coordinator needs to understand existing code paths. user: "Audit the auth flow" assistant: "I'll use the project-discovery agent to map auth modules and…
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…