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 jkomyno/.dotfiles --skill jk-reviewgit clone --depth 1 https://github.com/jkomyno/.dotfilesWrote 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/jkomyno/.dotfiles/jk-review)<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/jk-review"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-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/jkomyno/.dotfiles/jk-review"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-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 | $0.00039 | $0.01612 |
| Opus 5 | $0.00019 | $0.00806 |
| Sonnet 5 | $0.00008 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
jk-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 11d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jk-review
A review is a second pair of eyes, not a checklist. The job is to surface things the author can't see because they wrote it: load-bearing assumptions, scope creep, missing tests, drift from the repo's conventions, and silent regressions.
This skill produces a structured report. It does not auto-fix. The author decides what to address and when.
Scope
Review targets:
- Diff. Staged changes, branch vs main, or a specific commit range.
- Pull request. A GitHub PR (use
gh pr viewandgh pr diff). - Plan. A PLAN.md or similar before execution starts.
- Spec. A SPEC.md or similar before planning starts.
Not in scope:
- Style nitpicks the linter already catches. If the project has Biome, eslint, prettier, or rubocop wired up, trust them.
- Personal-preference rewrites. "I would have done it differently" is not a finding.
Protocol
- Identify the target. Diff, PR, plan, or spec. If ambiguous, ask.
- Read it in full once before forming opinions. Skim invites the kind of comment that misses context two paragraphs down.
- Read the surrounding code (for diffs and PRs). Open every file the diff touches and read the function before and after the changed lines. Many findings come from context the diff doesn't show.
- Build a findings list. Each finding gets a severity (P1/P2/P3), a one-line summary, a quoted location, and a concrete suggested action.
- De-duplicate. If three findings boil down to the same issue, merge them.
- Write the report. Markdown, in the structure below.
Severity definitions
Calibrate honestly. Severity inflation makes the whole report less useful.
P1 (blocks merge). Security vulnerability, data corruption risk, missing test for new behavior, broken backwards-compatibility on a stable API, factually wrong claim in a plan or spec, or anything that will cause an incident.
P2 (should fix before merge, but mergeable with author sign-off). Architectural drift, performance regression, naming inconsistencies that will calcify, missing error handling at a real boundary, ambiguity in a plan that would cost a re-spec cycle.
What ships with it
1 file 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.
- 11d ago First seen · 120 lines · 39 tokens per session scan A e39eb69e2676
jk-review is a skill published in the GitHub repository jkomyno/.dotfiles (5 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 1,612 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…