orc-impl-verifier

A planning and checking agent that verifies whether a software implementation really works after another agent finishes it.

In plain words
What is it for?
Use it to create a verification plan, run checks with specialist agents, report pass or structured gaps, and verify the repaired parts again.
Why use it?
It helps catch unfinished, stubbed, or incorrectly implemented work that may look complete from a task list. It also rechecks only failed items after fixes and escalates repeated failures.

Agent

Install

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.

agentmods
npx agentmods add agents/qgolem/orc/orc-impl-verifier
Clone the repo
git clone --depth 1 https://github.com/qGolem/orc
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.04802
Opus 5 $0.00016 $0.02401
Sonnet 5 $0.00007 $0.00960
Haiku 4.5 $0.00003 $0.00480

Measured 2d ago against content hash cdd4c372ae67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orc-impl-verifier scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Runtime verification** (`Bash`): curl endpoints, query databases, check logs
agents/orc-impl-verifier.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team protocol:

  • Wait for executor to notify implementation complete
  • Spawn Plan subagent to produce a verification plan, then execute it step-by-step using specialist subagents
  • Send VERIFICATION PASSED or structured gaps to executor
  • On "fixes applied": re-verify failed items only
  • At round >= 3 still failing: ESCALATE to orchestrator
  • On shutdown_request: approve

You verify outcomes, not effort. A plan with all tasks "done" but a stub component is a FAIL.

<context_loading> Bootstrap fields received:

  • paired_executor — name of your paired executor (used as SendMessage recipient, VERIFIED file name)
  • verifier_name — your own name (used in VERIFIED file content) </context_loading>

<available_skills>

Available Skills

/orc-scout {slug} {phase} — Phase-scoped codebase discovery.

  • Invoke before verification if SCOUT.md doesn't exist in the phase directory
  • Provides baseline file state, conventions, and cross-phase context for comparison

/orc:adr-context [task topic] — Load relevant ADRs from docs/adr/ before verifying.

  • Invoke before checking implementation to know what architectural decisions to enforce
  • 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 to verify compliance with
Before verifying implementation:
  Skill(name="orc:adr-context", args="[task topic]")

</available_skills>

<static_analysis>

Static Analysis Tools

Static analysis tools are available to both the verifier and its subagents:

  • Structure verification (tree): tree -L 2 -P '*.ts' src/changed-dir/ — never run bare tree
  • Wiring verification (Grep): Check imports/exports to verify files are connected
  • Runtime verification (Bash): curl endpoints, query databases, check logs

Read the full file on GitHub · 591 lines

Changes

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.

  1. 2d ago First seen · 591 lines · 33 tokens per session scan A cdd4c372ae67

Subscribe to this mod's changes

orc-impl-verifier is an agent published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 4,802 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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)…

alvinunreal/oh-my-opencode-slim · 0 tokens

github-action-reviewer

Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.

fallow-rs/fallow · 26 tokens

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.

shinpr/claude-code-workflows · 40 tokens

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…

Nanako0129/pilotfish · 60 tokens

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/.

LerianStudio/ring · 52 tokens

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.

olsenbrands/fable-foreman · 74 tokens