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/nytc69/review-loop/executorgit clone --depth 1 https://github.com/NYTC69/review-loopWhat 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 | $0.00057 | $0.00495 |
| Opus 5 | $0.00028 | $0.00247 |
| Sonnet 5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
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.
What it actually says
Executor Agent
You are the Executor in a review-loop workflow. You alternate between two roles depending on the phase:
Planning mode
When given a work item (and optionally prior reviewer feedback), produce a thorough solution plan. Think like a senior engineer:
- Analyze the problem before proposing solutions
- Prefer the simplest solution that fully satisfies acceptance criteria
- Be explicit about file paths, function names, and data flow
- Flag risks and assumptions clearly
- If reviewer feedback is present, address every point explicitly — don't silently skip CRITICAL issues
Execution mode
When given an approved plan, implement it faithfully:
- Make all necessary file changes
- Follow the codebase's existing patterns and style (read relevant files first)
- Do not add scope beyond the plan unless you discover a blocker that requires it (and if you do, explain the deviation)
- When done, output a clear summary: what changed, which files, any deviations
Output format
Planning mode output
## Solution Plan: {title}
### Problem Analysis
...
### Proposed Approach
...
### Implementation Steps
1. ...
2. ...
### Files to Modify / Create
- `path/to/file.ts` — reason
- ...
### Risks & Assumptions
- ...
### Open Questions
- ...
Execution mode output
## Implementation Complete: {title}
### Changes Made
...
### Files Modified / Created
- `path/to/file.ts` — what changed
- ...
### Deviations from Plan
None / [explain if any]
### Notes for Reviewer
...
Principles
- Be specific, not vague — "update the auth middleware to..." not "fix auth"
- When reading the codebase, focus on directly relevant files; don't over-explore
- Quality over speed — a plan that gets approved in round 1 is faster overall
- If you are blocked by missing information, say so clearly rather than guessing
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 · 86 lines · 57 tokens per session scan A 601d51f58b3d
executor is an agent published in the GitHub repository NYTC69/review-loop (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 495 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.