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 maintainer-replygit 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/maintainer-reply)<a href="https://agentmods.dev/skills/dannote/dot-pi/maintainer-reply"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/maintainer-reply/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/maintainer-reply"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/maintainer-reply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00803 |
| Opus 5 | $0.00032 | $0.00402 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
maintainer-reply 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Reply
Draft before posting. Read the relevant issue or PR conversation, repository guidance, and the user's stated goal before writing. A technically correct reply can still be wrong if it ignores what the recipient already knows or reveals private context.
Identify the reply
Before drafting, establish:
- recipient and relationship;
- issue, PR, review, or thread;
- purpose: answer, clarify, thank, apologize, request information, request changes, close, or explain a decision;
- what has already been said;
- what the recipient already knows;
- the state and time slice the reply must reflect, especially when testing or reconstructing an earlier point in a conversation;
- whether this is a draft or an approved post.
Keep these separate:
private reasoning → review findings, frustration, speculation, roadmap, internal comparisons
public reply → relevant facts, concrete request, brief rationale, appropriate next step
Do not leak private reasoning merely because it informed the decision.
Style
Write in the maintainer's natural voice:
- concise and humane;
- specific to this conversation;
- proportionate to the issue and contributor;
- direct without sounding automated or corporate.
Avoid generic filler, obvious restatements, excessive headings, long technical explanations, forced gratitude, unexplained jargon, and LLM-shaped phrases such as “I’ve provided detailed feedback below” when the context already makes that clear. Avoid intensifiers and stock support language such as “sincerely,” “we appreciate your effort,” and “thanks for your understanding” unless they fit the maintainer's established voice and this specific exchange. Do not mention bots, internal agents, or project politics unless the user explicitly wants that included.
Appreciate useful contributions sincerely. Do not treat a good-faith contributor like a low-effort or automated submission without clear evidence. If apologizing, name the concrete mistake and the correction; do not over-explain.
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.
- 6d ago First seen · 69 lines · 65 tokens per session scan A 25ec72591915
maintainer-reply is a skill published in the GitHub repository dannote/dot-pi (51 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 803 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
speq-code-review
Code review tag taxonomy and findings output format — guardrail violations, dead code, test quality, bad comments, optimizations, YAGNI/over-engineering, error handling, and design depth. Triggered by code-reviewer.
mine-plan-review
Strictly review one implemented repository plan against AGENTS.md, architecture, the immutable plan, implementation commits, real runtime behavior, verification evidence, and downstream contracts. Use when the user invokes the host-specific mine-plan-review skill with a plan path, asks whether a plan can be accepted…
regression-prevention
Implement or review non-trivial code changes while preserving contracts, repository conventions, user work, and affected behavior. Use for logic, refactors, dependencies, APIs, authentication, data, runtime, or tooling changes and for qualitative code review; exclude copy-only edits, explicit scoring requests, and…
multi-agent-security-review
Multi-agent workflow (tracer/resolver/bypass) for secure code review, exploitability triage, and PoC validation in codebases. Use when conducting structured security research or penetration test analysis.
multi-review
Multi-model code review. Runs code-review skill with 2 models in parallel, then synthesizes findings.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.