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 jmagly/aiwg --skill civic-publish-gategit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/civic-publish-gate)<a href="https://agentmods.dev/skills/jmagly/aiwg/civic-publish-gate"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/civic-publish-gate/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/jmagly/aiwg/civic-publish-gate"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/civic-publish-gate.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 | $0.00035 | $0.00366 |
| Opus 5.5 | $0.00014 | $0.00146 |
| Sonnet 5.5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
civic-publish-gate 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 1mo 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.
What it actually says
Civic Publish Gate
Process
- Supply a versioned publication packet with per-section count/freshness rules, claims, sources, links, structured-data validation, accessibility, privacy, correction state, static/CMS adapter results, and human review.
- Run
aiwg run skill civic-publish-gate -- packet.json. - Remediate every block. Warnings require visible human disposition.
- Treat automated accessibility checks as evidence only, never a complete WCAG conformance determination.
- Publication remains an external human action even after a machine pass.
- Verify the live page, last-good copy, sitemap, reindex, and cache handoffs; each must pass or be explicitly not applicable before publication completes.
Output
A schema-valid publication gate report. Exit 1 means blocked; exit 2 means
invalid input/usage. The command never writes to a CMS or external service.
References
schemas/publication-gate-result.schema.jsonrules/publication-human-review.mddocs/research/control-source-matrix.md- media-marketing-kit
qa-protocolandapproval-workflow; ops-completeops-verify
What ships with it
1 file 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.
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.
- 1mo ago First seen · 43 lines · 35 tokens per session scan A 071389249c97
civic-publish-gate is a skill published in the GitHub repository jmagly/aiwg (225 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 366 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
lifecycle-messaging
Email/SMS lifecycle and deliverability framework for SMB Product-Builder products that send transactional or lifecycle messages (booking reminders, CRM sequences, receipts, win-back). Codifies provider selection (Resend/Postmark/Twilio/SendGrid), domain auth (SPF/DKIM/DMARC), consent and compliance (TCPA, CAN-SPAM…
data-privacy
Use when a ticket handles personal data — collecting a new field about a person, exporting or deleting a user's data, retention and anonymisation, analytics events, sharing with a third party — and the change must minimise what is collected, protect it in storage and logs, honour deletion and access requests, and be…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
negotiator
Negotiation analyst for high-stakes deals: co-founder exits, business separations, contract terms, salary negotiations, investor terms. Use when the user asks to: (1) analyze a counterparty's position or message, (2) score/review a draft message before sending, (3) draft a counter-offer, (4) structure BATNA/ZOPA…
afc:consult
Expert consultation — backend, infra, PM, design, marketing, legal, or tech guidance.
compliance
Compliance expert for SOC 2, GDPR, HIPAA, PCI-DSS, and security frameworks.