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/thettwe/nyann/explain-statenpx skills add thettwe/nyann --skill explain-stategit clone --depth 1 https://github.com/thettwe/nyannWrote 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/thettwe/nyann/explain-state)<a href="https://agentmods.dev/skills/thettwe/nyann/explain-state"><img src="https://agentmods.dev/badge/skills/thettwe/nyann/explain-state.svg" alt="Measured on agentmods" 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 | $0.00166 | $0.00884 |
| Opus 5 | $0.00083 | $0.00442 |
| Sonnet 5 | $0.00033 | $0.00177 |
| Haiku 4.5 | $0.00017 | $0.00088 |
Grade A, and why
explain-state 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
explain-state
Read-only. Never mutates. Wraps bin/explain-state.sh.
1. Invoke
bin/explain-state.sh --target <cwd> [--json] [--profile <name>]
- No args → human-readable table, easy to read back to the user.
--json→ machine-readable JSON when the user wants to pipe it or you need structured fields for a follow-up operation.--profile <name>→ override profile inference when the user names one explicitly.
2. Read the output aloud
The JSON has six blocks. When the user asks a general "what's the state", summarize the highlights rather than dumping the whole structure:
- stack → "Detected
<primary_language>" + framework + package manager. Call outconfidence < 0.5as "weak detection — might be worth confirming". - profile → "Active profile:
<name>(source:<starter|user| team|unknown>)". When source isunknown, say "couldn't infer the profile; CLAUDE.md doesn't reference one". - branching → "Strategy:
<strategy>; base branches:<list>". If null, profile isn't resolved. - hooks → "Husky:
<bool>/ pre-commit.com:<bool>/ nyann core hooks:<bool>". These are presence signals only — they tell you whether something's wired, not whether it's healthy. For health, route todoctor. - claude_md → "CLAUDE.md present,
<bytes>bytes, router markers<bool>". Mention the 3 KB soft / 8 KB hard budget if bytes > 3072. - recent_commits → Mention the count; read back the 1-2 most recent subjects.
3. Follow-up routing
The whole point of explain-state is to help the user decide what to do next. Offer one or two next steps based on what's present:
- Stack but no profile → suggest
bootstrap-projectwith a matching profile name. - Profile but no hooks wired → suggest re-running
/nyann:retrofitto install the hook bundle. - CLAUDE.md missing router markers → note it can be regenerated via
/nyann:retrofit. - Everything present and clean → "Looks set up. Want a deeper audit?
Run
doctorfor drift checks."
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.
- 5d ago First seen · 85 lines · 166 tokens per session scan A 007af9f6e1a5
explain-state is a skill published in the GitHub repository thettwe/nyann (6 stars, last pushed 6d ago), licensed MIT. It adds 166 tokens to every session and 884 once invoked, about $0.0008 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
remember
Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
magic-compact
Compact this Claude Code session.
dream
Memory consolidation - review, merge, prune, and index memory files. Run periodically to keep memories organized and up-to-date.
import
Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.