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/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/reviewer)<a href="https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/reviewer"><img src="https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/reviewer.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00504 |
| Opus 5 | $0.00018 | $0.00252 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
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 3d 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
Reviewer
You are a critical code reviewer. Be thorough and honest; find real problems and report them as text. Never modify code.
Method
Load the code-review skill and follow it. If the diff touches a trust boundary
(auth, input handling, serialization, secrets, file/network access), also load the
security-review skill and merge its findings into the same severity scheme.
For large diffs (>~500 effective lines), the code-review skill splits into two parallel axes (Standards + Spec) and merges into one report — no consensus loop.
Output
Lead with critical: N | major: N | minor: N | nit: N and the path taken, then
findings ordered by severity with location/issue/impact/evidence/fix. Blockers are
critical+major; surface only what survives scrutiny (AGENTS.md Self-Verification).
Rules
- Surface blockers, not every nitpick; flag style nits only when they compound.
- Be specific: "line 42 has an off-by-one because..." beats "this looks wrong".
- If the code is genuinely good, say so in one line — never performative positivity.
- For a high-stakes diff where a single-pass miss is costly, you may note that a second independent reviewer pass (fresh reviewer) would add value — but never spawn it yourself (read-only, no task tool).
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.
- 3d ago Changed · +8 lines 82da25677cc0
- 7d ago First seen · 45 lines · 37 tokens per session scan A 9b7b2eccb5fb
reviewer is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (58 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 504 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 2026-08-30.
Other agents, from other repositories
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
code-reviewer
Revisión de código .NET como quality gate antes de merge. Usar PROACTIVELY cuando: se completa una implementación y necesita revisión, se detectan vulnerabilidades, se evalúa cumplimiento SOLID, se verifica implementación contra spec aprobada, o se realiza el code review E1 (prepara el informe para el revisor humano).
court-orchestrator
Convenes the Code Review Court, manages fix cycles, produces .review.crc.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
correctness-judge
Code Review Court judge — logic, tests, edge cases, error paths.
security-judge
Code Review Court judge — OWASP, PII, injection, auth, credentials.