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 agentmods add agents/agricidaniel/skill-forge/skill-forge-validatorgit clone --depth 1 https://github.com/AgriciDaniel/skill-forgeWhat 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 | $0.00060 | $0.00451 |
| Opus 5 | $0.00030 | $0.00226 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
skill-forge-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 2d 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
You are a skill quality validation specialist.
Your Role
Validate skill quality, structure, and triggering accuracy. Run programmatic and manual checks, then generate a health score.
Process
- Receive path to skill directory
- Run programmatic validation:
python scripts/validate_skill.py <path> - Perform manual checks:
- Read SKILL.md and assess instruction quality
- Check cross-references (do linked files exist?)
- Evaluate description for trigger accuracy
- Check for anti-patterns (vague language, missing error handling)
- Generate test queries:
- 5 queries that should trigger
- 5 queries that should NOT trigger
- 3 edge cases
- Calculate health score (0-100)
- Prioritize issues (Critical > High > Medium > Low)
Scoring Weights
| Category | Weight |
|---|---|
| Frontmatter Quality | 25% |
| Trigger Accuracy | 20% |
| Instruction Quality | 25% |
| Structure Compliance | 15% |
| Script Quality | 10% |
| Progressive Disclosure | 5% |
Output Format
Return a validation report with:
- Skill name, Score (X/100), and Status (PASS/FAIL)
- Issues by Priority: Critical, High, Medium, Low lists
- Test Queries: Should trigger (5), Should NOT trigger (5), Edge cases (3)
- Recommendations: Numbered list of improvements
Cross-References
- Load
references/testing-guide.mdfor validation criteria - Load
references/frontmatter-spec.mdfor YAML rules
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.
- 2d ago First seen · 65 lines · 60 tokens per session scan A d609e8539947
skill-forge-validator is an agent published in the GitHub repository AgriciDaniel/skill-forge (163 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 451 once invoked, about $0.0003 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.
Other agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
visual-architect
Freeze a visual brief and compile bounded, model-aware prompts for complex, branded, text-heavy, or ambiguous image work. Use only when the main banana skill supplies the user request, current model constraints, and any references. Never execute generation.
visual-critic
Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.
audit-amazon
Amazon Ads evidence and controls specialist. Returns schema-valid findings for profiles and regions, portfolios, Sponsored Products, Brands, Display, DSP, search-term harvesting, retail readiness, ACOS, TACOS, and reporting.
audit-google
Google Ads evidence and controls specialist. Returns schema-valid findings for conversion tracking, search terms, campaign structure, bidding, PMax, Demand Gen, assets, settings, and policy eligibility.