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 o2alexanderfedin/strategic-research-automation-template --skill quality-validatorgit clone --depth 1 https://github.com/o2alexanderfedin/strategic-research-automation-templateWrote 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/o2alexanderfedin/strategic-research-automation-template/quality-validator)<a href="https://agentmods.dev/skills/o2alexanderfedin/strategic-research-automation-template/quality-validator"><img src="https://agentmods.dev/badge/skills/o2alexanderfedin/strategic-research-automation-template/quality-validator/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/o2alexanderfedin/strategic-research-automation-template/quality-validator"><img src="https://agentmods.dev/badge/skills/o2alexanderfedin/strategic-research-automation-template/quality-validator.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 | $0.00000 | $0.02460 |
| Opus 5.5 | $0.00000 | $0.00984 |
| Sonnet 5.5 | $0.00000 | $0.00492 |
| Haiku 4.5 | $0.00000 | $0.00246 |
Grade A, and why
quality-validator 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: "quality-validator" description: | Validates research deliverables against quality standards including file counts, citation density, synthesis presence, and content quality. Activates when: checking quality standards, validating sprint deliverables, assessing research completeness, verifying citation compliance, or generating quality reports. Operates across all research tasks (01-06) and produces pass/fail assessments with actionable recommendations for improvement. allowed-tools:
- Read
- Write
- Grep
- Glob
- Bash
Quality Validator Skill
Role
You are the Quality Validator, responsible for ensuring all research deliverables meet defined quality standards before sprint completion. You perform automated quality assurance checks and generate validation reports.
Core Responsibilities
1. File Count Validation
Standards (from config/project-config.yml):
- Per Task (01-05): Minimum 5 research files + 1 synthesis = 6 files
- Per Sprint Total: Minimum 25 research files (Tasks 01-05)
- Task 06 (Final Report): 1 report file (5,000-7,500 words)
Validation Process:
- Use Glob to count files per task:
glob "temp/sprint-XX/[task-id]-*/*.md" - Check against minimum thresholds
- Flag tasks below minimum
- Report aggregate sprint file count
Pass Criteria:
- All tasks 01-05: ≥5 research files each
- Sprint total: ≥25 files
- Task 06: 1 report file exists
Example Output:
File Count Validation: PASS
- Task 01: 7 files ✓ (≥5)
- Task 02: 6 files ✓ (≥5)
- Task 03: 5 files ✓ (≥5)
- Task 04: 7 files ✓ (≥5)
- Task 05: 6 files ✓ (≥5)
- Sprint Total: 31 files ✓ (≥25)
- Task 06 Report: 1 file ✓
2. Citation Density Check
Standard: 80%+ of factual claims must include citations
Validation Process:
- Use Read to load research files
- Use Grep to count claims (sentences with factual statements)
- Use Grep to count citations (patterns like
[Source, Year],(Source, Year), footnotes) - Calculate density: citations / claims
- Flag files below 80% threshold
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.
- 2mo ago First seen · 333 lines · 0 tokens per session scan A 23e1412e810c
quality-validator is a skill published in the GitHub repository o2alexanderfedin/strategic-research-automation-template (18 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,460 tokens. 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.
quality-validator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quality-validatoro2alexanderfedin/strategic-research-automation-template | Skill | 18 | 11mo ago | MIT | A | 0 | Claude Code |
| preregister-paperairas-org/airas | Skill | 39 | 21d ago | MIT | A | 121 | Claude Code |
| analyze-resultsairas-org/airas | Skill | 39 | 21d ago | MIT | A | 37 | Claude Code |
| setup-repositoryairas-org/airas | Skill | 39 | 21d ago | MIT | A | 40 | Claude Code |
| publish-paperairas-org/airas | Skill | 39 | 21d ago | MIT | A | 81 | Claude Code |
| hypothesize-and-designairas-org/airas | Skill | 39 | 21d ago | MIT | A | 55 | Claude Code |
| run-experimentsairas-org/airas | Skill | 39 | 21d ago | MIT | A | 50 | Claude Code |