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 jimtin/production-ai --skill full-app-reviewgit clone --depth 1 https://github.com/jimtin/production-aiWrote 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/jimtin/production-ai/full-app-review)<a href="https://agentmods.dev/skills/jimtin/production-ai/full-app-review"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/full-app-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/jimtin/production-ai/full-app-review"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/full-app-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 | $0.00140 | $0.01836 |
| Opus 5 | $0.00070 | $0.00918 |
| Sonnet 5 | $0.00028 | $0.00367 |
| Haiku 4.5 | $0.00014 | $0.00184 |
Grade A, and why
full-app-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 10d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full App Review
Purpose
Use this skill when "fully review this app/repo" needs a fixed, repeatable meaning. The default outcome is an evidence-backed report plus prioritized remediation plan, not automatic code changes.
Operating Rules
- Do not mutate code, config, data, branches, dependencies, or deployment state unless the user separately asks for remediation.
- Start from repo truth: current instructions, scripts, routes, APIs, tests, env examples, deployment config, monitoring code, and live app structure.
- Build the review matrix before making conclusions. Use
references/review-matrix.md. - Assess the repo's existing error instrumentation and observability setup. Report gaps; do not impose a universal provider. Use
references/observability-checklist.md. - Use
references/report-template.mdfor the final report shape unless the user requests a different format. - Classify findings as
blocking,high,medium, orlow, and attach evidence, affected paths, required tests, and a concrete fix plan to each material finding. - If a repo-local
AGENTS.mdis stricter than this skill, follow the repo-local rules. - If review evidence is stale, missing, or blocked by auth/secrets/provider access, say so explicitly and mark the residual risk.
Specialist Skills
Use these skills as sub-workflows when their dimensions are in scope:
$frontend-design-quality: UI patterns, responsiveness, viewport fill, visual states, portals/admin flows, screenshots, and overflow checks.$feature-design-preflight: nontrivial workflows, provider limits, data/control flow, failure modes, UX states, and operational constraints.$test-readiness-preflight: coverage obligations, integration/E2E gaps, local/container gates, migrations, seeds, test doubles, and validation blockers.$repo-testing-setup: missing or incomplete testing foundation, host-only lanes, absent canonical containerized gate, undeclared hook/gate enforcement model, missing tooling matrix, missing committed workflow inventories, mis-scoped secret scanning, or missing provider stubs. In a review, report this as remediation; do not mutate.$user-action-coverage-review: the matrix format for user-action browser/E2E evidence. Express the testing dimension's user-action findings as its action matrix (action, surface, role, data state, evidence, status) so gaps convert directly into implementation tasks.$security-threat-model: trust boundaries, auth/authz, secrets, uploads, parsers, webhooks, admin paths, deployment surfaces, and abuse cases.$codebase-prune-review: redundant, superseded, legacy, dead, compatibility, or attack-surface-increasing paths.$nextjs-vercel-analytics: Next.js/Vercel analytics and custom-event instrumentation when analytics is explicitly in scope or already present.$error-logging-instrumentation: deep error-logging, runtime observability, structured logging, privacy/redaction, alerting evidence, and remediation when observability gaps need fixing.
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.
- 10d ago First seen · 108 lines · 140 tokens per session scan A f1982ac559af
full-app-review is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 1,836 once invoked, about $0.0007 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
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.