publish-record

publish-record is a skill for Claude Code from npstorey/civic-ai-tools. It costs 97 tokens per session (6,287 once invoked), scanned A, original, MIT.

A publishing tool for turning civic-data analysis into a signed, time-stamped record package logged in Rekor, a public system for recording tamper-evident entries.

In plain words
What is it for?
Use it after analysis with Socrata or Data Commons data when you want to publish, sign, or preserve the results as a record.
Why use it?
It gives a completed analysis a verifiable publication record that others can check later.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/foo/Code/civic-ai-tools.

Good fit Use it after analysis with Socrata or Data Commons data when you want to publish, sign, or preserve the results as a record.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 publish-record

README.md
[![agentmods](https://agentmods.dev/badge/skills/npstorey/civic-ai-tools/publish-record/github.svg)](https://agentmods.dev/skills/npstorey/civic-ai-tools/publish-record)
Your own site
<a href="https://agentmods.dev/skills/npstorey/civic-ai-tools/publish-record"><img src="https://agentmods.dev/badge/skills/npstorey/civic-ai-tools/publish-record/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.

agentmods 80×15 button for publish-record

Your own site · 80×15
<a href="https://agentmods.dev/skills/npstorey/civic-ai-tools/publish-record"><img src="https://agentmods.dev/badge/skills/npstorey/civic-ai-tools/publish-record.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00097 $0.06287
Opus 5 $0.00048 $0.03143
Sonnet 5 $0.00019 $0.01257
Haiku 4.5 $0.00010 $0.00629

Measured 11d ago against content hash ce11294ce564, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

publish-record 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (publish.py, test_publish.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.

.claude/skills/publish-record/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

publish-record

This skill turns the current Claude Code conversation's civic-data analysis into a signed record package on civicaitools.org (the default target — see "Publishing to a different instance" below). It wraps POST /api/records; the endpoint contract lives in civic-ai-tools-website/docs/api/records-publish.md.

Renamed from publish-evidence by the 2026-08-19 vocabulary settlement (specification Appendix J: "evidence" is retired as the artifact/infrastructure name and retained only for the epistemic Question/Evidence/Claim role). The old invocation still works.claude/skills/publish-evidence/ remains as a permanent alias that routes here. There is one publish.py, in this directory; the alias never carries a copy.

When to invoke

The user has just finished an analysis in this session using the Socrata MCP server (mcp__socrata__* tools) and/or the Data Commons MCP server (mcp__data-commons__* tools). They now want to publish the analysis as a verifiable record. Typical phrasings:

  • "publish this as a record"
  • "publish this as evidence" (the prior-era phrasing; still routes here)
  • "publish to civicaitools.org"
  • "sign this analysis"
  • "make this a verifiable package"

Do not invoke this skill for analyses the user has not asked to publish, or for non-civic conversations (code questions, chit-chat, etc.). Do not invoke it to re-publish a package that was already published in this session; just quote the URL from the prior turn.

Capture modes

The skill supports two capture modes. Pick the one that matches what the user said, set captureMode in the JSON payload, and proceed.

Mode When to choose it What gets captured
single_final_turn (default) "publish this as a record", "publish this as evidence", "publish this analysis", "sign this answer" — the user points at a single question → answer cycle. The last user prompt, the final assistant markdown response, and every civic MCP tool call made to answer it. Matches the website chat-flow shape.
full_conversation "publish this whole session", "publish the full conversation", "include every turn", "publish everything we did" — the user wants the multi-turn record. Every captured turn since the civic analysis started, rendered as a markdown transcript in output, plus every civic MCP tool call across those turns. Emits a structured turn list in extensions["org.civicaitools.multi-turn"].

Read the full file on GitHub · 234 lines

Files

What ships with it

2 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. 11d ago First seen · 234 lines · 97 tokens per session scan A ce11294ce564

Subscribe to this mod's changes

publish-record is a skill published in the GitHub repository npstorey/civic-ai-tools (41 stars, last pushed 6d ago), licensed MIT. It adds 97 tokens to every session and 6,287 once invoked, about $0.0005 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.