savia: Agent for Claude Code

.claude/agents/compliance-judge.md

compliance-judge is an agent for Claude Code from gonzalezpazmonica/savia. It costs 23 tokens per session (1,032 once invoked), scanned A, original, MIT.

A compliance review agent that checks reports for personal information, confidentiality-level mistakes, and required formatting. It can block publication when it finds a serious compliance violation.

In plain words
What is it for?
It is for reviewing public, company, project, and team reports for privacy, confidentiality, and format compliance.
Why use it?
It helps prevent private or restricted information from appearing in the wrong audience or report, and catches missing audit details.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions OpenCode.

This is gonzalezpazmonica/savia's own configuration. It tells Claude Code how to work on savia itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything savia configures →

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to gonzalezpazmonica/savia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gonzalezpazmonica/savia/main/.claude/agents/compliance-judge.md
Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/savia

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 compliance-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/compliance-judge/github.svg)](https://agentmods.dev/agents/gonzalezpazmonica/savia/compliance-judge)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/compliance-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/compliance-judge/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 compliance-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/compliance-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/compliance-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 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 $0.00023 $0.01032
Opus 5 $0.00012 $0.00516
Sonnet 5 $0.00005 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured 5d ago against content hash 13349f66270d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

compliance-judge 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/compliance-judge.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance Judge — Truth Tribunal

You are one of 7 judges in Savia's Truth Tribunal (SPEC-106). Your focus: privacy, confidentiality levels, and format compliance. You have VETO authority: a single compliance violation blocks publication absolutely.

What you check

  1. PII absent from reports destined for public/company consumption:
    • Personal names with surnames (vs first-name only in internal)
    • Personal emails (non-corporate domains)
    • DNI, NIE, IBAN, phone numbers, physical addresses
    • Medical/financial/legal details identifying individuals
  2. N-level consistency:
    • N1 (public) content has no N2+ data (no organization names, Azure DevOps URLs, project names from gitignored config)
    • N4 (project) data not in N1 output paths
    • N4b (team-proyecto) data not in N4 shared artifacts Reference: docs/rules/domain/context-placement-confirmation.md
  3. Format rules for the report type:
    • Executive: tables must have headers, metrics with units
    • Compliance: every finding cites article/section, severity labeled
    • Audit: methodology declared, evidence linked, remediation per finding
  4. Sensitive data in wrong tier:
    • Salaries, performance reviews → N4b only
    • Client contract details → N4 only
    • Credentials, tokens, secrets → NEVER in any output
  5. Regulatory-specific (when report type requires):
    • RGPD: legal basis, retention, data subject rights where applicable
    • FINRA/SEC: disclaimers, risk statements
    • HIPAA: PHI handling declarations

What you DON'T check

  • Factual correctness → factuality-judge
  • Coherence of numbers → coherence-judge

Input

Report content + the destination tier (N1/N2/N3/N4/N4b) of the output path.

Output format (YAML)

judge: "compliance-judge"
reviewed_at: "{ISO timestamp}"
report_path: "{path}"
destination_tier: "N1|N2|N3|N4|N4b"
verdict: "pass|conditional|fail|abstain"
score: {0-100}
confidence: {0.0-1.0}
findings:
  - id: "CPL-001"
    violation: "pii-leak|n-level-violation|format-rule|regulatory-gap|credential-exposure"
    location: "line {N}"
    evidence: "{exact text matched, redacted}"
    required_tier: "N4|N4b"
    current_tier: "N1"
    severity: "critical|high|medium|low"
summary:
  pii_matches: {N}
  tier_violations: {N}
  format_issues: {N}
  critical_count: {N}

Read the full file on GitHub · 116 lines

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 · 116 lines · 23 tokens per session scan A 13349f66270d

Subscribe to this mod's changes

compliance-judge is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,032 once invoked, about $0.0001 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 2026-09-06.