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-thread-verifygit 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-thread-verify)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/review-pr-thread-verify"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/review-pr-thread-verify/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-thread-verify"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/review-pr-thread-verify.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 | $0.00627 |
| Opus 5.5 | $0.00025 | $0.00251 |
| Sonnet 5.5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
review-pr-thread-verify 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 1mo 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
review-pr-thread-verify
Decide what has happened to one review finding since we posted it. The caller hands over everything; this skill judges and returns, and never posts, resolves, or edits anything itself.
Receives. The original finding (its anchor, body, the commit or head SHA it was reviewed at, and the concrete concern it raised); every author reply on the thread since our last message, plus every prior reply we posted there; the current code at the anchor with nearby context, and any commits since the original review that touched the relevant range; the full PR history (all comments, review threads, commit messages, the current PR description, our prior review and comment bodies); bundle context for each linked PR (diff, description, top-level conversation); and the caller's voice profile — its rules for how a posted comment reads — to apply to any reply drafted here.
Judges. Read the concrete concern first and hold it fixed: the question is whether that failure mode is gone, conceded, disproven, or still live — not whether the thread has been discussed. A code change counts only when it touches the relevant range and removes the failure mode; a reply counts only when a fair-minded human reviewer would concede it. Push back only on new signal — a new author reply or a code change — and stay on the specific point under contention; never repeat an argument already made on the thread.
Returns exactly one disposition:
addressed-by-fix— A commit after our review modified the relevant code and removes the concrete failure mode. Straightforward code fixes need no reply unless there was active discussion to answer; draft one only then.addressed-by-valid-reply— The author replied on this or another thread with an argument a fair-minded human reviewer would concede: correct factual context, a deliberate owner trade-off, a valid out-of-scope boundary, or code elsewhere already covering the concern. Draft a short concession or acknowledgment.false-positive-or-stale— Our comment was wrong, stale, or is disproven by current PR history. Draft a brief correction that owns the miss.needs-our-pushback— The author replied or changed code, but the concrete concern remains. Draft a short reply for the existing thread on that specific point.still-pending— No relevant new author reply and no relevant code change since our last look. Draft nothing.
Return shape. The disposition name, one short reason (the evidence: the commit, the reply, or the absence of either), and the drafted reply text when the disposition calls for one, written in the supplied voice profile.
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.
- 1mo ago First seen · 24 lines · 63 tokens per session scan A 2d12058f0486
review-pr-thread-verify 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 627 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.