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 dannote/dot-pi --skill dont-anger-mariogit clone --depth 1 https://github.com/dannote/dot-piWrote 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/dannote/dot-pi/dont-anger-mario)<a href="https://agentmods.dev/skills/dannote/dot-pi/dont-anger-mario"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/dont-anger-mario/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/dannote/dot-pi/dont-anger-mario"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/dont-anger-mario.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 108 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00046 | $0.00855 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
dont-anger-mario 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 10d 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.
Don't Anger Mario
Use this skill before opening an issue or contribution proposal in earendil-works/pi.
Rules
- Read
CONTRIBUTING.mdfirst. - Use an official issue template; blank issues are disabled.
- Keep it short. If it does not fit on one screen, it is too long.
- Write in the user's own voice, not corporate/AI slop.
- Be concrete: what, why, and optionally how.
- Do not submit automatically.
- Before submitting, ask the user to confirm they carefully read the exact final draft and explicitly approve posting it.
- If proposing a change, use Contribution Proposal rather than Bug Report.
- If reporting a bug, include minimal repro and version.
- If opening a PR, only proceed after maintainer approval (
lgtmfor PRs;lgtmiis issues only). - Do not send agent-only PRs. If the user cannot explain the change without the agent, stop.
Safe workflow
- Inspect templates and contributing docs:
gh api repos/earendil-works/pi/contents/.github/ISSUE_TEMPLATE --jq '.[].name'
gh api repos/earendil-works/pi/contents/CONTRIBUTING.md --jq .content | base64 --decode
- Draft the issue body in
/tmp, never inline long Markdown through shell quoting:
cat > /tmp/pi-issue.md <<'EOF'
### What do you want to change?
...
### Why?
...
### How? (optional)
...
EOF
-
Show the exact final title and body to the user.
-
Ask for explicit approval with this wording:
Please read the draft carefully. Do you explicitly approve me posting this issue/proposal as written?
Do not proceed on vague approval like "ok" if the user has not seen the exact final draft.
- Create only after explicit approval:
gh issue create \
--repo earendil-works/pi \
--template contribution.yml \
--title "Short concrete title" \
--body-file /tmp/pi-issue.md
Extra caution from prior tracker behavior
Known maintainer reactions that shape this workflow:
- Auto-close gate is intentional; maintainers review closed issues later.
- GitHub Actions outages can let the issue/PR gate fail and flood the repo.
- Maintainers dislike agent-only PRs because they take time to review and are often broken.
- "Clanker misunderstood the code" is a real failure mode; verify the claim before drafting.
- A label/comment like
possibly-openclaw-clankeris a warning sign: shorten, verify, and make the human reasoning obvious.
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.
- 10d ago First seen · 113 lines · 46 tokens per session scan A b9a27a457ee2
dont-anger-mario is a skill published in the GitHub repository dannote/dot-pi (51 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 855 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
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
temporal-developer
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or…
cafleet
Interact with the CAFleet message broker and supervise CAFleet member teams. Use when an agent needs to register as a member, send/receive messages, poll inbox, acknowledge messages, or discover other members; or when a Director is about to spawn, monitor, health-check, or recover a stalled team of CAFleet members…
speq-implement
Orchestrate implementation of a reviewed plan: task breakdown, TDD sub-agents, code review, and verification report. Use when the user asks to implement, build, or execute a plan under specs/plans/ — after /speq-plan, before /speq-record. Arg: .
speq-plan-pr
Headless, non-interactive version of /speq-plan for CI or agent-driven runs. Plans a feature without a live interview, commits the result to a feat/plan-name branch, and opens a draft PR. If a decision genuinely needs a human, it persists the partial plan and open questions and asks in a PR comment instead of…
anycap-human-interaction
Collect structured visual feedback from humans using AnyCap's annotation tool, or create and iterate on diagrams using the interactive whiteboard (Excalidraw). Covers image annotation, URL/web page review with screen recording, video review, audio feedback, and collaborative diagramming with Mermaid input. Use when…