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 doodledood/manifest-dev --skill review-pr-judgmentgit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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/doodledood/manifest-dev/review-pr-judgment)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/review-pr-judgment"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/review-pr-judgment/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/doodledood/manifest-dev/review-pr-judgment"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/review-pr-judgment.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 | $0.00063 | $0.01718 |
| Opus 5.5 | $0.00025 | $0.00687 |
| Sonnet 5.5 | $0.00013 | $0.00344 |
| Haiku 4.5 | $0.00006 | $0.00172 |
Grade A, and why
review-pr-judgment 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 20d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-pr-judgment
The reviewer-fleet dimensions find defects inside a change whose intent is taken as given — they judge implementation against explicit requirements and weigh the author's rationale as evidence. The judgment pass adds the one thing they structurally cannot: it asks whether the change earns its keep — whether it should exist, in this shape, at this footprint, given the pain it claims to solve.
The single question: Does this change — its existence, its approach, and its footprint — earn its keep against the pain it solves, and is anything the pain requires missing?
It runs as a wide-context pass. Receives: the PR description, the PR conversation, the codebase direction, the full PR-head diff (base..head, the whole PR), and, in manifest mode, the manifest's Intent as the stated pain — context the narrow-lens defect reviewers never see. It is non-blocking: every finding is a question the author answers, never a gate. The caller decides where this runs and gates fresh generation to once per PR; this skill only judges and returns.
Altitude — whole-PR only
The judgment pass operates on the PR as a whole, or a major component of it — the big question, never line-level ones. It must never fire on a small-item nitpick — an unused parameter, a single narrow helper, one incidental line; those belong to the defect dimensions or are dropped. The surface, omission, and precedent triggers fire only on a material footprint: a subsystem, a new public API area, a cluster of knobs, an established pattern — never a single incidental item.
Whole-PR altitude is unconditional: whenever the pass runs, it reads the entire PR head, not just the incrementally-reviewed range on a loop or re-review pass, so its question always concerns the whole change. Judgment findings are therefore exempt from any reviewed-range bounding that scopes defect findings to the latest delta.
The evidence bar
The pass exists to remove noise (unjustified changes, orphaned surface). It becomes noise the instant it fires on taste. So every trigger fires only on concrete, nameable evidence — something you can point at. "I'd have done it differently" is not evidence and stays dropped, just as implementation review requires evidence rather than a competing preference. When in doubt, stay silent: a missed premise question costs less than an arrogant one.
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.
- 20d ago Changed 928db3428e54
- 1mo ago Changed f95ba3707b6d
- 1mo ago First seen · 83 lines · 63 tokens per session scan A 3b55f1dcca17
review-pr-judgment is a skill published in the GitHub repository doodledood/manifest-dev (75 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,718 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
well-architected
6-pillar architecture review framework. Adapted from AWS Well-Architected for use by greatcto's architect agent on every non-nano ARCH document. Forces explicit answers across operational excellence, security, reliability, performance, cost, and sustainability — not just feature design.
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.