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/koolamusic/claudefiles/servegit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/commands/koolamusic/claudefiles/serve)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/serve"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/serve.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 | $0.00056 | $0.00728 |
| Opus 5 | $0.00028 | $0.00364 |
| Sonnet 5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
serve 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serve the sprint corpus as a browsable review site: sidebar of sprints (collapsible, docs in read order, APPROVE/REVISE badges parsed from each CHECK.md), a STATE page when .jira/STATE.md exists, and optional extra sections for any markdown directory.
Steps
-
Parse flags from the arguments:
--port(default8081),--only(comma list of doc names without.md— default is ALL markdown files per sprint),--include <dir>[:Title](repeatable — appends a markdown directory as a named section; e.g.--include .project/rfc.one:RFCs),--title(site title, defaults to<repo-basename> · Sprint Review). -
Build. From the repo root run:
node ${CLAUDE_PLUGIN_ROOT}/scripts/serve-site.mjs --root "$(git rev-parse --show-toplevel)" [pass-through flags]The script resolves a GFM renderer from the host project's own
node_modules(micromark+gfm, marked, or markdown-it — direct or via the pnpm store) and falls back to a built-in mini renderer when none exists. Output goes to/tmp/jira-serve/<repo-basename>/(override with--out). It never writes inside the repo. -
Serve. If the port is free, start a static server in the background:
python3 -m http.server <port> --directory /tmp/jira-serve/<repo-basename> --bind 0.0.0.0(Fallback when python3 is absent:
npx -y serve -l <port> /tmp/jira-serve/<repo-basename>.) If the port is already serving a previous run of this command, just rebuild — the server picks up the new files on refresh. If the port is held by something else, report it and pick the next free port. -
Report the URL(s) —
http://localhost:<port>plus the machine's LAN address when available — the page count, what was included/filtered, and the one-line rebuild command for mid-review refreshes.
Rules
- Read-only with respect to the repository: the site is built OUTSIDE the repo; never add build output or server artifacts to git.
- Re-running rebuilds from scratch (the out dir is wiped first) — safe to run after every doc change.
- The server is a convenience for review, not a deployment: bind-all is fine on trusted networks; mention
ssh -Ltunneling for anything else. - Sprints are ordered most-recently-modified first; docs within a sprint follow read order (BRIEF, RESEARCH, CONTEXT, features/*.feature, numbered plans, CHECK, ISSUE-DRAFT, then the rest).
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 · 37 lines · 0 tokens per session scan A b1c3ffc80d07
serve is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 728 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 2026-08-30.
Other commands, from other repositories
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间，成员权限，团队组织.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.