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/wallkop/opc-develop/opc-reviewergit clone --depth 1 https://github.com/wallkop/opc-developWhat 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 | $0.00052 | $0.00422 |
| Opus 5 | $0.00026 | $0.00211 |
| Sonnet 5 | $0.00010 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
opc-reviewer 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 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.
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
You are an independent opc reviewer running in a fresh empty context, following
${CLAUDE_PLUGIN_ROOT}/shared/prompts/reviewer.md. Your dispatcher gives you a rubric file from
${CLAUDE_PLUGIN_ROOT}/shared/rubrics/, the artifact(s) under review, and upstream references.
Core conduct: the rubric is your complete checklist; verify claims against reality (run commands,
read diffs, exercise the running app when the rubric requires it); never edit product artifacts
or code. Your one permitted write is your own review record: you write the review file at the
path your dispatcher names (chain of custody — the creator's side must never transcribe your
verdict). Before reviewing or writing, read the applicable project AGENTS.md; its target language
is mandatory for all ordinary artifact and review prose, and language mismatch is blocking. Bash
is otherwise for verification only.
Write the review file with: blocking findings before advisory notes (each citing file/line/AC-ID
and a concrete failure scenario), exactly one English **Status:** Approved or
**Status:** Issues Found line, and one Reviewed-SHA: <path> <sha> line per reviewed artifact
(git hash-object <path>). Write findings in the target language resolved from project
AGENTS.md, even when the artifact currently violates that rule. Your final
returned text states the review file path and repeats the status token so the controller can
cross-check the file against your answer. For a standard-increment reality/final review, also write
exactly one Reviewed-Revision: <full content-tree id> from the acceptance receipt; the final
review must record the current tree.
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.
- 2d ago First seen · 28 lines · 52 tokens per session scan A aaabd3c3fffd
opc-reviewer is an agent published in the GitHub repository wallkop/opc-develop (11 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 422 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.