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 commands/thettwe/nyann/plangit clone --depth 1 https://github.com/thettwe/nyannWhat 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 | $0.00088 | $0.00595 |
| Opus 5 | $0.00044 | $0.00298 |
| Sonnet 5 | $0.00018 | $0.00119 |
| Haiku 4.5 | $0.00009 | $0.00060 |
Grade A, and why
nyann:plan 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.
What it actually says
Plugin root: This is a Claude Code plugin, NOT a CLI tool. Do NOT
search via which, npm list, pip list, or brew list. This file
is at <plugin_root>/commands/. All scripts: <plugin_root>/bin/.
Read the matching skills/*/SKILL.md for the full flow.
/nyann:plan
Wraps bin/iac-plan.sh. READ-ONLY IaC preview — it never applies. Flow:
- Confirm there's an infra signal (a tool name, "infra"/"deploy"
intent, or a detected
.iac.tool). If not, this is the wrong skill. - Run
bin/iac-plan.sh --target <cwd> [--unit <path>]→ IacPlan JSON. - Branch on
.status:planned→ render add/change/destroy summary;skipped→ surface the missing CLI/backend/creds, do NOT offer apply;refused→ fix the bad input (unknown tool / unit traversal). - For a destructive plan, AskUserQuestion before offering apply.
.status |
Meaning |
|---|---|
planned |
A plan ran — render the summary. |
skipped |
CLI/backend/creds absent (exit 0) — nothing to apply. |
refused |
Bad input (exit 1) — unknown tool or --unit traversal. |
Structured tools (terraform/opentofu/aws-cdk/pulumi) report real counts; advisory tools (helm/kubernetes/kustomize/ansible) emit a text diff only, counts are 0, and the change is treated as potentially destructive.
See skills/iac-plan/SKILL.md for the full flow and the DISAMBIGUATION
that keeps /nyann:plan off the bare word "plan" (project/sprint
planning, ExitPlanMode). To apply after previewing → /nyann:apply.
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 · 49 lines · 88 tokens per session scan A db7d89050c07
nyann:plan is a command published in the GitHub repository thettwe/nyann (6 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 595 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 commands, from other repositories
create-namespace
Slash command that creates a new namespace file under system/namespaces/ in the personal repo, with lifecyclestate: scratch.
oss
Daily OSS contribution check - uses CLI with --json for structured data.
setup-oss
Configure OSS autopilot preferences.
forge
You are in FORGE MODE. Execute the following.
run-tests
Run tests across all MyACE components (backend, frontend, CLI).
optimize-costs
Find cost savings in infrastructure without sacrificing quality or performance.