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 Tx1207/hello-scholar --skill reviewgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/review)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/review"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/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/tx1207/hello-scholar/review"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00747 |
| Opus 5.5 | $0.00023 | $0.00299 |
| Sonnet 5.5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
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 9d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Find what could invalidate the proposed decision or break the required behavior under its actual conditions. Use independent expectations, concrete counterexamples, and evidence to separate a material problem from an open question or a preference.
Review is read-only by default and needs no Spec. If the user asks for review and repair, establish the findings first, then continue with the repairs and their verification.
Establish what the judgment covers
Identify the object and the state actually inspected: a Spec's path, revision, and status; the commit and in-scope working-tree changes for code; the inputs, Run Records, and results for evidence. Read the connected material needed to understand it. Judge a proposal as a proposal: code not yet written is not a design defect. Keep the reviewed material and generated Indexes unchanged, and run only checks the existing authorization covers.
Challenge the consequential assumptions
Derive what should happen from the user outcome, confirmed rules, and real contracts, independently of the implementation and its tests. If those sources disagree, show the conflict instead of picking the version that passes.
- For a design, connect its promise to the mechanism, assumptions, resource limits, and interactions required to deliver it, and seek a realistic case it cannot handle.
- For code, trace inputs, state changes, failures, and outputs through the relevant callers. Confirm a suspected trigger is reachable and the consequence follows. Similar code or an extra layer is not unnecessary complexity until you identify that it serves no responsibility or contract.
- For research, check whether the comparison and measurement support the claimed interpretation. Distinguish failed execution, an inconclusive comparison, a valid negative result, and evidence for adoption; look for incompatible conditions, omitted contrary results, or an unseparated alternative explanation. Check whether an existing Run could have answered the question before a new one was launched.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 35 lines · 58 tokens per session scan A 1a568467a354
review is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 747 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…