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 skills add Parslee-ai/neo --skill neo-reviewgit clone --depth 1 https://github.com/Parslee-ai/neoWrote 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/skills/parslee-ai/neo/neo-review)<a href="https://agentmods.dev/skills/parslee-ai/neo/neo-review"><img src="https://agentmods.dev/badge/skills/parslee-ai/neo/neo-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/parslee-ai/neo/neo-review"><img src="https://agentmods.dev/badge/skills/parslee-ai/neo/neo-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00885 |
| Opus 5 | $0.00025 | $0.00443 |
| Sonnet 5 | $0.00010 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
neo-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neo Code Review
When the user invokes this skill ($neo-review <file or module>), do the following:
-
Identify the target. It will usually be a file path (e.g.
src/api/handlers.py), a module name, or a free-form description ("the payment processing code"). Use Read/Grep/Glob to resolve it to concrete file(s). -
Read the relevant code. Up to 5 files at a time keeps Neo's context budget healthy. Prefer the files where the actual logic lives over generated/test files.
-
Apply the provider boundary. Redact secrets, credentials, tokens, cookies, and session material. Before an external-provider call, tell the user which Neo provider will receive which files or data categories. Production, private, or customer code requires explicit authorization for that provider and scope; invoking the skill is not blanket consent.
-
Invoke Neo with a review-framed prompt. Allow up to 5 minutes. Use Codex's approval flow for required network access, naming the provider and summarized data in the approval description.
neo --json --no-scan --no-memory --mode advise <<'QUERY' Review the following code for: security vulnerabilities, edge cases, error handling, performance issues. Provide concrete suggestions with confidence scores. <paste relevant code or summarize what you read> QUERY -
Filter Neo's output to review-relevant findings. Group by severity. Flag any finding with confidence ≥ 0.8 as actionable; treat lower-confidence findings as worth-checking-but-verify.
-
Cross-reference with Neo's KNOWN ISSUES IN NEARBY CODE section if present. Neo's context-assembly already surfaces TODOs, stubs, swallowed exceptions, hardcoded credentials — those overlap with review concerns and add weight to related findings.
--no-scan is mandatory: Codex already selected the review files, so Neo must
not silently add working-directory files to the provider request.
--no-memory is the default so unrelated stored facts cannot enter the provider
prompt. Omit it only when the user explicitly authorizes relevant Neo memory;
include stored facts as a disclosed data category.
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.
- 12d ago First seen · 70 lines · 50 tokens per session scan A 651da5bc21bd
neo-review is a skill published in the GitHub repository Parslee-ai/neo (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 885 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…