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 blakecyze/kanso --skill kanso-promptinggit clone --depth 1 https://github.com/blakecyze/kansoWrote 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/blakecyze/kanso/kanso-prompting)<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-prompting"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-prompting/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/blakecyze/kanso/kanso-prompting"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-prompting.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 | $0.00051 | $0.01582 |
| Opus 5 | $0.00026 | $0.00791 |
| Sonnet 5 | $0.00010 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
kanso-prompting 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kanso-prompting
Standing rules for prompting current frontier models. These principles apply to any prompt this session produces, including prompts being constructed on the user's behalf.
The single governing principle: a prompt earns its length the same way code does. Every clause must do work. Specificity beats verbosity; clarity beats cleverness; structure beats hope.
The prompting taxonomy
1. Lead with the desired outcome
State what the model should produce, in what shape, for what audience, before any context. Don't bury the ask under preamble.
Bad: I've been working on this codebase for a while and I noticed that the auth module has some issues, particularly around session handling, and I was wondering if maybe you could take a look...
Good: Audit src/auth/session.ts for race conditions in session creation. Report findings as a numbered list with file:line references.
2. Explain the why, not just the what
Reasons let the model generalise correctly to cases you didn't spell out. Without the why, it follows the letter and misses the spirit.
Bad: Never use ellipses.
Good: Never use ellipses — the output will be read aloud by a TTS engine that can't pronounce them.
3. State what to do, not what to avoid
Negative-only instructions trigger the behaviour they warn against and leave a vacuum where positive guidance should be. Replace every "don't" with a "do".
Bad: Don't use markdown.
Good: Write in flowing prose paragraphs.
4. Front-load the full task in turn one
For coding and agentic work, ambiguous first turns produce worse results than a single dense first turn. Specify task, scope, constraints, and definition of done upfront. Don't rely on follow-up turns to recover.
5. Show, don't tell — examples beat description
Two or three concrete examples steer the model more than a paragraph of instruction. Use diverse examples that cover edge cases, not three rewrites of the same shape.
6. Structure complex prompts with tags
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 · 119 lines · 51 tokens per session scan A 95b6134f7708
kanso-prompting is a skill published in the GitHub repository blakecyze/kanso (3 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 1,582 once invoked, about $0.0003 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
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
composer-prompting
Internal guidance for shaping a well-specified coding task into a tight Cursor/Composer prompt before delegating it via /cursor:delegate.
ccc-prompt-fix
Fix and sharpen a prompt. Diagnoses it against the 6 prompt-quality patterns, returns a tightened rewrite with the reasoning, and suggests the right library prompt for your task.
factory-prompting
Structured prompting with XML tags. A small named vocabulary (instructions, context, input, outputformat, examples, constraints, role, thinking) that turns a prose ask into something the model can parse without ambiguity. Read whenever you're authoring a prompt by hand, designing a prompt template for production, or…