klimkit-report-server

klimkit-report-server is a skill for Claude Code, Codex from klimentij/klimkit. It costs 77 tokens per session (566 once invoked), scanned A, original, MIT.

A local service for making static HTML proof reports in a repository available to inspect, including through Tailscale URLs. Tailscale is a private network service that can connect approved devices.

In plain words
What is it for?
Use it to check report-server readiness, serve docs/work HTML reports, verify /reports/ links, and troubleshoot Tailscale Serve.
Why use it?
It provides a fallback when the session cannot publish reports through its normal hosted tools. It also helps diagnose whether report files and links are reachable.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/klimentij/klimkit/klimkit-report-server
Any agent
npx skills add klimentij/klimkit --skill klimkit-report-server
Clone the repo
git clone --depth 1 https://github.com/klimentij/klimkit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for klimkit-report-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-report-server.svg)](https://agentmods.dev/skills/klimentij/klimkit/klimkit-report-server)
Your own site
<a href="https://agentmods.dev/skills/klimentij/klimkit/klimkit-report-server"><img src="https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-report-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00566
Opus 5 $0.00039 $0.00283
Sonnet 5 $0.00015 $0.00113
Haiku 4.5 $0.00008 $0.00057

Measured 5d ago against content hash f191a6c1d9b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

klimkit-report-server 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/serve_reports.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/klimkit-report-server/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Klimkit Report Server

Use this skill to make proof reports reachable and inspectable. This is the fallback serving path: the default for human-facing HTML is the harness's native hosted surface — the Claude Code Artifact tool or Codex Sites, both authentication-protected and private by default. Reach for this skill when no native hosted surface is available in the session, when the report must be served from the repo tree, or when troubleshooting existing report serving. The skill owns a small reference server script so report hosting can live with the skills package instead of depending on deprecated Klimkit runtime code.

Workflow

  1. Ensure Klimkit's docs-first context exists. If the repo lacks the docs/work/ layout, use klimkit-setup first.
  2. Identify the repository root and expected report locations:
    • Default: self-contained numbered HTML artifacts anywhere under docs/work/ (excluding gitignored .local/ folders)
    • Legacy readable fallback: .klimkit/reports/ and .klimkit/<operator>/reports/
  3. Check local report files before checking network serving.
  4. If no report server is running, use scripts/serve_reports.py as the reference implementation or copy it into the target repo when the user asks for a persistent local setup.
  5. If a local report server is configured, check the local /reports/ URL.
  6. If Tailscale is available, check the machine DNS name and the /reports/ Tailscale URL.
  7. If serving is unavailable, report the missing layer precisely:
    • no report HTML exists;
    • local server is not running;
    • Tailscale is not authenticated;
    • a tailnet proxy is not forwarding to the local report server;
    • permissions require operator setup.
  8. Do not claim a Tailscale URL works until it has been fetched or otherwise verified in this session.

Report Expectations

  • HTML reports should be self-contained single files, tracked when they are part of work proof.
  • Large screenshots/videos should usually stay in a gitignored .local/ folder as local media referenced by the report.
  • Report media should render full-width for inspection.
  • Prefer MP4 presentation embeds when Chrome/PWA scrubbing matters.

Read the full file on GitHub · 36 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 36 lines · 77 tokens per session scan A f191a6c1d9b5

Subscribe to this mod's changes

klimkit-report-server is a skill published in the GitHub repository klimentij/klimkit (7 stars, last pushed 26d ago), licensed MIT. It adds 77 tokens to every session and 566 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.

Related

Other skills, from other repositories

production-prep

Última etapa. Revisão técnica (ortografia, gramática, consistência) + formatação para ebook e impresso. Dois especialistas num só. Usar após todas as revisões de conteúdo estarem prontas, antes de publicar ou submeter.

felipelobomotta-blip/book-genesis-v4 · 56 tokens

book-auto

One-command book generation. Give it an idea, get a publish-ready book. Dispatches the book-orchestrator agent which runs the entire 17-phase pipeline autonomously, pausing only at 3 human checkpoints.

felipelobomotta-blip/book-genesis-v4 · 47 tokens

expense-report-generation

How to turn raw card and bank statement downloads into a defensible, client-ready expense report. Use whenever the user asks to build an expense report, reconcile AmEx or bank statements, work out "what is this charge for", aggregate reimbursables for a client or trip, split a claim by month, or render an expense PDF…

lossless-group/lossless-agent-skills · 181 tokens

lossless-flavored-markdown

The Lossless Group's extended-markdown flavor — what LFM is, when to use it, how its directives normalize across syntaxes (CommonMark, GFM, Obsidian callouts, remark-directive, Markdoc), how citations and link previews work, and how sites extend it via trigger maps and theme tokens. Use whenever authoring or rendering…

lossless-group/lossless-agent-skills · 158 tokens

tmcp-repo-behavior-spec-loop

Use TMCP for repo-wide behavior specification loops: code-derived feature inventory, canonical spreadsheet tracking, running-app verification, defect remediation, regression coverage, and final evidence audits.

jakyeamos/tmcp · 0 tokens

html-output

Convert the current plan, spec, design doc, or conversation context into a single self-contained, share-able HTML file with rich visual structure (tables, SVG diagrams, code blocks, responsive layout, in-page navigation). Supports four output shapes — editorial, technical-doc, dashboard, and slide-deck. Use when the…

Rijul1204/rashedul-agentic-engineering · 142 tokens