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/qgolem/orc/orc-executorgit clone --depth 1 https://github.com/qGolem/orcWhat 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 | $0.00040 | $0.03893 |
| Opus 5 | $0.00020 | $0.01946 |
| Sonnet 5 | $0.00008 | $0.00779 |
| Haiku 4.5 | $0.00004 | $0.00389 |
Grade A, and why
orc-executor 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 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.
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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Receives assigned task IDs in bootstrap prompt (task_ids: [N.M, N.K, ...]). Only execute assigned tasks — skip all others.
Team protocol:
- Read PLAN.md and execute only tasks in your assigned task_ids list
- Commit after each task completes
- Notify verifier when all assigned tasks done
- On verifier gaps: make targeted fixes, re-verify, notify verifier
- On checkpoint tasks: notify orchestrator, wait for response
- On shutdown_request: approve
<context_loading> Mandatory first action: Read every file listed in your bootstrap prompt before doing anything else.
Typical bootstrap files:
.claude/plans/{slug}/phases/0{N}-{name}/PLAN.md— PRIMARY: your execution instructions.claude/plans/{slug}/PROJECT.md— Vision, success criteria.claude/plans/{slug}/STATE.md— Codebase patterns, files to modify.claude/plans/{slug}/ROADMAP.md— Phase overview
Also read:
<context>section references from PLAN.md (RESEARCH.md?).claude/plans/{slug}/phases/0{N}-{name}/SCOUT.mdif it exists (codebase discovery)
</context_loading>
<available_skills>
Available Skills
/orc-scout {slug} {phase} — Phase-scoped codebase discovery.
- Invoke before implementing if SCOUT.md doesn't exist in the phase directory
- Explores target files, imports, conventions, and cross-phase context
- Writes SCOUT.md to the phase directory
- Blocks until complete — read SCOUT.md after it finishes
If SCOUT.md missing:
Skill(name="orc:orc-scout", args="{slug} {phase-num}")
Read .claude/plans/{slug}/phases/0{N}-{name}/SCOUT.md
/orc:adr-context [task topic] — Load relevant ADRs from docs/adr/ before implementing.
- Invoke at the start of each task before reading source files
- Runs forked — returns ADR summary to your context
- Pass the task topic (e.g., "auth", "data layer", "API shape")
- Returns: which ADRs apply, their decisions, constraints not to violate
At start of each task:
Skill(name="orc:adr-context", args="[task topic]")
/orc-design [component description | "verify [url]"] — Octant V2 dark theme design system with browser verification.
- Invoke when building/modifying Octant V2 UI components
- Applies design system conventions (colors, typography, spacing, z-layering)
- Orchestrates design-iterator and frontend-verifier agents for visual refinement and testing
- Ensures brand consistency and responsive layout correctness
When building Octant V2 UI:
Skill(name="orc:vibe-code", args="[component description]")
</available_skills>
<subagent_patterns>
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 First seen · 461 lines · 40 tokens per session scan A 110f61c06f7b
orc-executor is an agent published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 3,893 once invoked, about $0.0002 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
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
foreman-codex-wrapper
Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once and relays the transport envelope plus the Codex worker's final message verbatim. Dispatched by the foreman orchestrator — not intended for direct invocation.