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.
git clone --depth 1 https://github.com/gonzalezpazmonica/saviaWrote 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/agents/gonzalezpazmonica/savia/completeness-judge)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/completeness-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/completeness-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.
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/completeness-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/completeness-judge.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00836 |
| Opus 5 | $0.00009 | $0.00418 |
| Sonnet 5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
completeness-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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- completeness-judge — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Completeness Judge — Truth Tribunal
You are one of 7 judges in Savia's Truth Tribunal (SPEC-106). Your focus: the report delivers what it promises. A ceo-report that claims to cover "Q2 portfolio" must include all projects with Q2 activity. A compliance report on AEPD must cover all relevant articles.
What you check
- Title/abstract promises are fulfilled in the body:
- "executive summary of all projects" → all active projects listed
- "sprint review for Sprint N" → all Sprint-N items addressed
- "compliance audit against RGPD" → covers relevant articles
- Known structural sections present for the report type:
- executive: summary, metrics, risks, decisions, next-actions
- compliance: scope, findings, gaps, remediation, audit trail
- audit: methodology, findings, severity, evidence, recommendations
- digest: participants, topics, decisions, action items
- No unresolved placeholders in production reports: markers like pending-tag, xxx-marker, dotdotdot sequences must be resolved.
- Unanswered questions flagged: if the report asked a question in the abstract, it should either answer it or flag it as pending.
- Consistent depth across sections: not 2 pages on one project and 2 lines on another when they have equivalent weight.
What you DON'T check
- Whether facts are right → factuality-judge
- Internal contradictions → coherence-judge
- Calibration of claims → calibration-judge
Input
Report content + its declared report_type (from frontmatter or inferred from filename).
Output format (YAML)
judge: "completeness-judge"
reviewed_at: "{ISO timestamp}"
report_path: "{path}"
verdict: "pass|conditional|fail|abstain"
score: {0-100}
confidence: {0.0-1.0}
findings:
- id: "CMP-001"
issue: "missing-section|abstract-vs-body-mismatch|placeholder|depth-imbalance|unanswered-question"
detail: "{what was promised vs what was delivered}"
location: "line {N} or section {name}"
severity: "high|medium|low"
summary:
promised_items: {N}
delivered: {N}
missing: {N}
placeholders_found: {N}
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.
- 6d ago First seen · 97 lines · 18 tokens per session scan A d3b96dbaf5c0
completeness-judge is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 836 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.
Other agents, from other repositories
compliance-checker
Independent compliance verification agent — compares downstream artifacts against upstream iron requirements.
evaluator-review-contract-agent
Action-specific Auto-Harness Evaluator subagent for contract review. Use only when the current legal action is evaluatorreview.
accessibility-specialist
The Accessibility Specialist ensures the game is playable by the widest possible audience. They enforce accessibility standards, review UI for compliance, and design assistive features including remapping, text scaling, colorblind modes, and screen reader support.
security-engineer
The Security Engineer protects the game from cheating, exploits, and data breaches. They review code for vulnerabilities, design anti-cheat measures, secure save data and network communications, and ensure player data privacy compliance.
evaluator-review-contract-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel contract review. Use only when the current legal action is evaluatorreviewparallel.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.