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 jerseycheese/agent-skills --skill kissgit clone --depth 1 https://github.com/jerseycheese/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/jerseycheese/agent-skills/kiss)<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/kiss"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/kiss/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/jerseycheese/agent-skills/kiss"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/kiss.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 | $0.00072 | $0.00544 |
| Opus 5 | $0.00036 | $0.00272 |
| Sonnet 5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
kiss 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KISS — Keep It Minimal
Purpose
Given a diff or staged changes, strip everything down to the smallest set of modifications that achieves the stated goal. Nothing more.
What to remove or simplify
- Refactors or restructuring not required by the fix
- Variable/function renames that aren't part of the stated goal
- Comment additions or edits beyond the changed lines
- Import reordering or cleanup
- Whitespace normalization unrelated to the change
- "While I'm here" fixes — flag these as separate tasks instead
- New abstractions or helpers not required by the change
- Extra test coverage beyond what directly tests the change
- Style or formatting changes outside the modified logic
What to simplify (overengineering)
- Constants or data structures that wrap what could be inline literals
- Helper functions called only once — inline them
- Intermediate variables that just rename what they hold
- Multi-step logic that can be a single expression
- Generic/parameterized code where one concrete case exists
- Abstractions built for hypothetical future callers
- Overly defensive null checks or fallbacks for impossible states
- Tests with elaborate setup for simple assertions — simplify the fixture
Process
- Identify the stated goal — what is this change trying to do? One sentence.
- Read the full diff —
git diff HEADorgit diff --staged - For each hunk, ask: is this hunk strictly required to achieve the goal? If no, mark it for removal.
- Separate the extras — list anything removed with a one-line reason; offer to file each as a standalone task.
- Apply the trimmed diff — edit files to remove the extras, keeping only what's necessary.
- Verify — run tests on the trimmed change to confirm it still achieves the goal.
Rules
- Prefer editing one line over editing a function; prefer editing a function over editing a file.
- A change that touches N files should touch N-1 files if possible.
- If in doubt about whether something is necessary, remove it and note it.
- Never introduce new patterns or dependencies in a KISS pass.
- Flagged extras go into a list at the end — never silently dropped.
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 · 51 lines · 72 tokens per session scan A 24aa418b0e93
kiss is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 9d ago), licensed MIT. It adds 72 tokens to every session and 544 once invoked, about $0.0004 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
chorus-council
Run an LLM council — Claude (correctness), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope) tackle the same task in parallel. Use when the user wants multiple independent perspectives on a decision, approach, or problem.
chorus-parallel-review
Parallel code review of the current git diff from multiple agents — Claude (correctness/security), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope/simplicity). Use when the user says "parallel review", "review with all agents", or "chorus review".
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
qa
Full QA on all session changes using Codex as a second pair of eyes. Use when user says "QA", "full QA", "QA my changes", "QA all your changes", or "use codex to review". Runs git diff, sends changes to Codex for thorough review, and synthesizes findings.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…