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 yugash007/edu-agent-skills --skill project-reviewgit clone --depth 1 https://github.com/yugash007/edu-agent-skillsWrote 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/yugash007/edu-agent-skills/project-review)<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/project-review"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/project-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/yugash007/edu-agent-skills/project-review"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/project-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 | $0.00034 | $0.00758 |
| Opus 5 | $0.00017 | $0.00379 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
project-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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Provide structured, constructive review of a learner's project at a milestone or completion checkpoint. Combines technical evaluation with learning-outcome assessment. Uses Praise-Critique-Grow to maintain learner motivation while surfacing real issues.
Activation
- Milestone reached in
build-with-me. Feature or project completed. Learner asks for feedback on their work. Pre-submission review (assignment, portfolio, interview take-home). - Skip if: project hasn't started. Learner needs concept help →
teach-concept. Active debugging in progress →debug-teacher. - Routing: issues found → use
challenge-generatorfor targeted practice. Concept gaps →teach-concept. Design issues →architecture-review. Log weak areas toweak-area-tracker.
Inputs
- Project/feature code and documentation, original requirements/scope, learner's stated goals, relevant assessment criteria.
Review Dimensions
- Scope: does it meet stated requirements? Scope creep? Missing features?
- Correctness: does it produce correct results? Edge cases handled?
- Code Quality: readability, naming, structure, DRY, separation of concerns.
- Testing: test coverage, test quality, edge case testing.
- Learning Outcomes: what did the learner demonstrate they understand? What gaps remain?
Workflow
- Self-Assessment — Ask learner first: "What do you think went well? What would you change?" This surfaces their self-awareness before external feedback.
- Review — Evaluate across all 5 dimensions. Note strengths and issues with specific code/design references.
- Praise — Start with 2–3 specific strengths. Reference actual decisions/code, not generic compliments.
- Critique — List issues priority-ordered. Each: dimension, description, severity, specific code reference. Max 5 issues per review — more overwhelms.
- Grow — For each major issue: one concrete next action. Frame as growth opportunity, not failure. Include a learning recommendation (skill or concept to revisit).
- Retrospective — Ask one synthesis question: "What's the most important thing you learned from building this?" Record answer for
learning-memory.
What ships with it
2 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.
- 12d ago First seen · 64 lines · 34 tokens per session scan A f8c44b14a932
project-review is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 758 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
receiving-code-review
Processes review feedback until the change is approved.
hatch3r-enhancability-verify
Enhancability verification gate before commit/release — feature-flag adoption on behavior changes, config externalization, semver-versioned APIs, forward-compat headers, extension-point definition, startup config validation.
hatch3r-maintainability-verify
Maintainability verification gate before commit/release — jscpd duplication index, pattern reuse ratio, cyclomatic complexity, expand-contract migrations, API breaking-change discipline, ADR presence.
kotlin-review
Review Kotlin tests, architecture, or ABI compatibility, over the working tree, a commit, a pull request, or the whole repository.
install-codex-agents
Install this plugin's Kotlin review agents into Codex, which cannot load agents from a plugin.
call-codex
Use when the codex CLI should be driven from the agent — as a reviewer giving a second, independent opinion ("ask codex", "call codex", "codex review", "get a second opinion", "challenge this finding"), or as an executor doing a scoped task in the repository ("have codex do this", "delegate this to codex", "let codex…