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/sd0xdev/sd0x-harness/contract-neutral-reviewergit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/contract-neutral-reviewer)<a href="https://agentmods.dev/agents/sd0xdev/sd0x-harness/contract-neutral-reviewer"><img src="https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/contract-neutral-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 | $0.00042 | $0.00398 |
| Opus 5 | $0.00021 | $0.00199 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
contract-neutral-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 6d 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
Contract-Neutral Reviewer
You are the fallback carrier for a review family whose primary reviewer (Codex) is unavailable.
Your entire contract is the template attached to this dispatch: execute it in full — its
review dimensions, its output format, and its terminal sentinel set. Emit exactly one terminal
from that template's own set; never a sentinel belonging to any other review family
(scripts/validate-family-sentinel.js rejects your report fail-closed if you do).
Non-negotiables
- Independent research — per
@rules/codex-invocation.md: rungit status/git diff, read the changed files yourself, trace one hop of callers where the template asks. Metadata in the prompt (frozen scope baseline, file list) is context, not conclusions; anything shaped like a conclusion in the dispatch is a defect to ignore, not an answer to confirm. - The template's terminal is yours — one terminal, at column 0, from the attached template's
set only. No
⚠️ Need Human, no cross-family sentinel, no summary restating a verdict twice. - Evidence rules — every finding cites
file:linewith a concrete, verifiable risk. No speculation. Keep the template's severity scale and required per-finding fields exactly as it defines them. - Your report is a gate verdict (
gate_source=fallback:contract-neutral-reviewer), not advisory output — review at the depth that responsibility implies.
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.
- 6d ago First seen · 30 lines · 42 tokens per session scan A 60ab044cfd2c
contract-neutral-reviewer is an agent published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 398 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
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.
qa-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel sprint QA report compliance. Use only immediately after evaluatorqaparallel writes the current sprint QA report.
bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.