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 Lingtai-AI/lingtai --skill pr-review-deliverablesgit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/pr-review-deliverables)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/pr-review-deliverables"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/pr-review-deliverables/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/lingtai-ai/lingtai/pr-review-deliverables"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/pr-review-deliverables.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 76 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00078 | $0.01763 |
| Opus 5 | $0.00039 | $0.00881 |
| Sonnet 5 | $0.00016 | $0.00353 |
| Haiku 4.5 | $0.00008 | $0.00176 |
Grade A, and why
dev-guide-pr-review-deliverables 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 13d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review & Deliverables
Nested lingtai-dev-guide reference. Read this after the top-level router sends you here to prepare a PR for review, build its human-facing explainer, and run review gates before asking for a merge.
It consolidates the PR-review-gate, HTML-explainer, deliverable-template, and release-style-audit practices, covering preparing and reviewing PRs and their human deliverables. Release publication is outside this bundled guide — use the dedicated release owner available in the maintainer's environment.
Core principle
A PR is review-ready only when (1) the diff is clean and validated, (2) a self-contained HTML explainer tells the human the story, and (3) the change has passed at least one independent review pass. Opening, editing, and merging PRs are external side effects: do them only after an explicit maintainer authorization for that side effect.
1. PR readiness gate
- Clean diff:
git diff --check(no trailing whitespace / conflict markers). - Targeted tests for the changed area pass; record commands and results.
- If you touched utility/dev-guide skills, the nested-reference tests and the root router catalog/routing table were updated in the same commit.
- Anatomy travels with code: any moved/renamed/split file cited by an
ANATOMY.mdis updated in the same commit. - No secrets, tokens, or private absolute paths in the diff or the explainer.
- A self-contained HTML explainer exists (see §3).
Known repo pitfalls: docs/stars/stars.csv may use CRLF intentionally — do not
"normalize" it; and portal tests may need frontend assets built first
(npm --prefix portal/web run build).
2. Independent review passes (gates, not permission)
Run at least one independent, read-only review pass before merge. Strongest first:
- Multi-model / daemon review. Generate a diff prompt and have a read-only
daemon (Claude Code / Codex) or a second model review correctness, scope, and
regressions. Save the review as an artifact so it is auditable. Run API-backed
reviewers with keys from the environment (
<API_KEY_ENV>), never inline. - Claude review gate. A focused Claude Code review of the diff for correctness bugs and reuse/simplification cleanups.
- Self review against the readiness gate (§1).
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.
- 13d ago First seen · 147 lines · 78 tokens per session scan A c9ac2a7aa857
dev-guide-pr-review-deliverables is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 1,763 once invoked, about $0.0004 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…