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 agentmods add skills/ariaxhan/kernel-claude/simplifynpx skills add ariaxhan/kernel-claude --skill simplifygit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWhat 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 | $0.00030 | $0.01118 |
| Opus 5 | $0.00015 | $0.00559 |
| Sonnet 5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
simplify 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapted from saurabhkumar8112/cyclomatic-complexity-skill (Apache-2.0), with one change: the refactoring model never signs its own before/after table. A verifier re-measures.
<on_start> agentdb recall "simplify complexity <files/symbols>" --global </on_start>
Exit 3 means no lizard and no uvx. Say so and count by hand (decision points + 1:
if, elif, case, loops, catch, ternary, &&/|| in conditions). Never skip silently.
Ladder (default, project config outranks it):
- 1 to 5: leave alone
- 6 to 10: refactor only if already touching
- 11 to 15: refactor now
- over 15: must split
<hard_rules>
- Preserve behavior. Tests before and after. Same inputs, same outputs, same errors.
- Do not game the metric. A dense one-liner hiding six branches is worse than the honest if-chain it replaced. Complexity moves into named units; it never disappears into cleverness. A CCN drop with a rising token count per line is the tell.
- Do not change public APIs or exported signatures without asking.
- One responsibility per function. If the name needs "and", split again.
- Small functions with clear names beat few functions with section comments. </hard_rules>
ACCEPTANCE: every function in the before table is at or under the after value claimed
ACCEPT WHEN: complexity.sh re-run matches the claimed after table; tests pass; no exported signature changed
CHECK: ${CLAUDE_PLUGIN_ROOT}/scripts/complexity.sh <repo> <base-ref>; <test command>; git diff <base-ref> -- <files> | grep -E '^[-+](def |export |func |pub fn )'
ESCALATE IF: any function's re-measured CCN exceeds the claim, or a one-liner replaced a branch without a name
DISCOVERY AXIS: invariant
Builder and verifier identities go on the receipt. The builder never fills in "behavior verified".
Extracted: validate_header, resolve_discount Tests: <pass/fail before> -> <pass/fail after> Verified by: (re-measured: match | mismatch)
Keep prose minimal. Numbers and diffs do the talking.
</output>
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.
- 2d ago First seen · 107 lines · 30 tokens per session scan A 23e16ac39222
simplify is a skill published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,118 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 2026-08-30.
Other skills, from other repositories
prolong
Recover and use durable coding-session history from PRO-LONG's local append-only log. Use on long-running coding tasks, after context compaction or session resume, when reconstructing prior decisions or tool results, or before repeating work that may already have been attempted.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
causal-memory
Causal memory for agents — install/setup the causal-memory MCP server, then record decisions/outcomes and recall them before acting. Trigger when the user asks to install or set up causal-memory/agent memory, when causal-memory MCP tools are available and the agent faces a non-trivial decision (architecture, debugging…
a0-create-plugin
Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.
a0-review-plugin
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
create-skill
Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users want to create custom skills.