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/baz-scm/baz-plugin/get-plan-commentsnpx skills add baz-scm/baz-plugin --skill get-plan-commentsgit clone --depth 1 https://github.com/baz-scm/baz-pluginWrote 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/baz-scm/baz-plugin/get-plan-comments)<a href="https://agentmods.dev/skills/baz-scm/baz-plugin/get-plan-comments"><img src="https://agentmods.dev/badge/skills/baz-scm/baz-plugin/get-plan-comments.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 | $0.00055 | $0.02217 |
| Opus 5 | $0.00028 | $0.01108 |
| Sonnet 5 | $0.00011 | $0.00443 |
| Haiku 4.5 | $0.00006 | $0.00222 |
Grade A, and why
get-plan-comments 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan comments
You were invoked to bring a Baz plan's review comments back into this session.
This skill reports before it writes. Step A reads the comments and shows the user a summary. Step B applies the ones they pick. You never run Step B off your own reading of Step A — not even for comments the reviewer marked Use.
The two-step structure is your procedure, not something the user needs to hear about. Never narrate it: no "Phase 1", no "read-only pass", no "nothing was written", no restating these instructions. The user asked about their plan's comments — show them the comments.
Which plan
mcp__baz__get_plan_comments takes one argument, planId — the UUID in the plan URL https://baz.co/plans/<planId>.
A plan pushed by an agent session is stored under that session's id, so the two are the same UUID:
- This session pushed the plan — pass your own session id as
planId. - Any other case (a new session, someone else's plan) — take the UUID from the plan URL.
$ARGUMENTSmay already hold it; accept a bare UUID or a full URL.
If you have neither, ask for the plan link rather than guessing.
Step A — read, assess, report
No writes here. None. No respond_to_plan_comment, no update_plan, no edits to the plan file.
-
Call
mcp__baz__get_plan_comments. It returns four groups:Group Meaning Show as recommendedMarked Use, no replies yet — the reviewer wants these considered ✅ Use awaitingTriageNo Use/Skip decision recorded 🕒 Open alreadyRepliedMarked Use and carrying replies — you answered on an earlier run, or a discussion is live. The thread is included, so read it before assuming 💬 Use · N replies skippedMarked Skip — a one-line gist only ⏭️ Skipped Any group can carry a
repliesarray, not justalreadyReplied— an untriaged comment with a live argument on it shows up underawaitingTriagewith its thread attached. Wheneverrepliesis non-empty, say so in the State cell (Open · 2 replies) and write the thread out below the table.
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.
- 4d ago First seen · 109 lines · 55 tokens per session scan A 2f2b553fe045
get-plan-comments is a skill published in the GitHub repository baz-scm/baz-plugin (10 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 2,217 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 2026-08-31.
Other skills, from other repositories
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步（architecture-sync）。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档（Observed/Inferred 分层 · Mermaid 真源）。OpenCode / Claude / Codex / Cursor 通用。.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.