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-principlesgit 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-principles)<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-principles"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-principles/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-principles"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-principles.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 | $0.00043 | $0.01290 |
| Opus 5 | $0.00022 | $0.00645 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
kanso-principles 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kanso-principles
Standing context for any code-related task. These rules override default verbosity and defensive habits. They apply equally to code you write, code you review, and code you modify.
The single governing principle: prefer deletion over addition. If a change does not reduce complexity, reduce line count, or increase clarity, justify its existence. Code earns its place.
The anti-dilution taxonomy
1. No tautological comments
A comment must explain why, not restate what. If the comment echoes the code, delete the comment or rewrite it to carry business context, constraints, or intent.
Bad: // Filter users by age above users.filter(u => u.age > 18).
Good: // Legal requirement: 18+ only above the same line.
2. No temporal or step-marker comments
Artefacts of the prompt that produced the code. Delete them before they commit.
Bad: // Step 1: fetch user, // Now validate, // Add retry logic as requested
Good: no comment, or a comment explaining why the retry exists.
3. No defensive programming theatre
Cascading try/catch, null checks on already-typed values, isinstance checks on typed parameters, and exception handlers that silently swallow errors and return None/null. Silent errors are the deadliest errors.
Let exceptions propagate. Handle them at the boundary where the recovery strategy is known. If an invariant is guaranteed by the type system, trust it.
4. No filler variables
const result = compute(x); return result; is just return compute(x);
Intermediate variables earn their place by adding a meaningful name or being referenced more than once.
5. No zero-entropy names
userDataProcessingResult, helperFunction, dataManager. Statistically probable, domain-free, and unreadable at a glance.
Prefer: adults, invoice, sessionExpired. Short names are fine when the context makes them clear.
6. No premature abstraction
A factory for one implementation, an interface for one consumer, a base class for one subclass. These are costs without benefits. Solve the problem that exists now, not one that might exist later.
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.
- 9d ago First seen · 113 lines · 43 tokens per session scan A b8b74e3ec58d
kanso-principles is a skill published in the GitHub repository blakecyze/kanso (3 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 1,290 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
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…
skill-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.