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-cligit 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-cli)<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/jk-cli"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-cli/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-cli"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-cli.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 | $0.00041 | $0.01833 |
| Opus 5.5 | $0.00016 | $0.00733 |
| Sonnet 5.5 | $0.00008 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
jk-cli 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jk-cli
jk is @jkomyno's personal assistant CLI: it performs deterministic,
mechanical tasks for coding agents and local workflows with stable flags,
stable machine-readable output, and meaningful exit codes. It never calls
LLMs, reads model-provider API keys, makes network calls to a model, or makes
judgment calls. Treat it as a predictable tool, not an assistant — same input,
same output, every time.
The binary is jk (on PATH at ~/.local/bin/jk). Four commands:
| Command | Reach for it when… |
|---|---|
whoami |
You need the GitHub login the gh CLI is authenticated as (read offline). |
notify |
A script/hook/long command should ping a phone via Telegram. |
actions |
A repo's GitHub Actions refs need pinning to SHAs or an update report. |
idea |
You need to acquire, index, or search a reference corpus under ~/.jk/ideas. |
The output contract (read this before parsing anything)
jk auto-detects its consumer:
- Piped / non-TTY stdout (agents, scripts, hooks) → JSON. This is the stable API. Parse it; never scrape the human text.
- Interactive terminal → human-readable text.
- Force either way with the global
--json <BOOL>:--json=trueor--json=false. It is POSIX-style and the last one on the line wins.
Because an agent's stdout is piped, jk already emits JSON to you by default —
no flag needed. Add --json=false only when showing a human the text form.
stdout carries only the data payload; all diagnostics, progress, and errors
go to stderr.
Exit codes (branch on these, not on text)
| Code | Meaning | Examples |
|---|---|---|
0 |
success | normal completion; idea search found ≥1 hit |
1 |
command findings | actions check found drift; idea search found no hits (grep-style) |
2 |
usage error | missing/invalid flags, bad subcommand |
3 |
operational error | network failure, idea index could not convert a document, wrapped command failed |
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.
- 1mo ago First seen · 156 lines · 41 tokens per session scan A f20417eb945b
jk-cli is a skill published in the GitHub repository jkomyno/.dotfiles (5 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,833 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 2026-08-31.
Other skills, from other repositories
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
start-temps-cluster
Start (or restart) a local multi-node Temps cluster using Docker-in-Docker — one control plane + 3 worker nodes, each a privileged DinD container running its own dockerd + temps agent, wired with the real multi-host overlay (VXLAN, computecidr allocation) via tools/dev-cluster/ in whichever checkout/worktree you run…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.