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 JetXu-LLM/DocMason --skill validation-repairgit clone --depth 1 https://github.com/JetXu-LLM/DocMasonWrote 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/jetxu-llm/docmason/validation-repair)<a href="https://agentmods.dev/skills/jetxu-llm/docmason/validation-repair"><img src="https://agentmods.dev/badge/skills/jetxu-llm/docmason/validation-repair/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/jetxu-llm/docmason/validation-repair"><img src="https://agentmods.dev/badge/skills/jetxu-llm/docmason/validation-repair.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 | $0.00024 | $0.00625 |
| Opus 5 | $0.00012 | $0.00313 |
| Sonnet 5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
validation-repair 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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation Repair
Use this skill when the knowledge base needs validation, repair, or publication follow-through.
This is an internal follow-on workflow behind knowledge-base-sync.
Ordinary users should not need to invoke it by name.
Required Capabilities
- local file access
- shell or command execution
- ability to read machine-readable validation reports
If the agent cannot run docmason validate-kb or inspect the reported errors, stop and explain that reliable repair is not possible.
Procedure
- Use
stagingas the default validation target unless the task explicitly says otherwise. - Run
docmason validate-kb --json.- keep DocMason workspace commands sequential inside one live workspace session
- do not overlap
validate-kbwithsync,status,retrieve, ortraceagainst the same workspace while leases may still be active
- Inspect the
blocking_errors,warnings, and per-source reports inknowledge_base/<target>/validation_report.json. - Fix the staged source or interaction-memory files that caused the failures:
- missing or stale
knowledge.json - missing or malformed
summary.md - unresolved citations
- unresolved
artifact_idcitations - invalid related-source links
- missing or malformed
artifact_index.json - missing or malformed
pdf_document.json - missing or malformed
semantic_overlay/*.json - invalid
render_page_span, artifact refs, or sidecar asset references - placeholder or incomplete bilingual content
- missing or stale
- Rerun
docmason validate-kb --jsonuntil the result isvalidorwarnings. - When staged validation is no longer blocking, return control to the main agent so it can rerun
docmason sync --jsonfor final publication.
Escalation Rules
- If validation reveals a capability or evidence gap that cannot be repaired honestly, stop and surface that blocker instead of weakening the quality gate.
- If a fix would require changing derived retrieval or trace artifacts directly, do not hand-edit them. Regenerate them through the supported workflows.
- If the failure is in deterministic sidecars such as
artifact_index,visual_layout,spreadsheet_*, orpdf_document, repair the upstream staged source inputs or rerun the supported compiler path instead of hand-editing the derived files. - Final publication remains a main-agent step.
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.
- 10d ago First seen · 58 lines · 24 tokens per session scan A 589f77e64eef
validation-repair is a skill published in the GitHub repository JetXu-LLM/DocMason (135 stars, last pushed 6d ago), licensed Apache-2.0. It adds 24 tokens to every session and 625 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 2026-08-30.
Other skills, from other repositories
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
dbt-transformation-patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
dataset-evaluation
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model…
coverage-tracker
Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.
prompt-set-qa
Gate a prompt universe for schema and provenance completeness, target or campaign contamination, evidence entailment, naturalness, one-concept clarity, architecture consistency, aided status, answer leakage, and semantic duplicates. Use after realistic prompt generation and before human panel selection.
realistic-prompt-generation
Generate natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved jobs, acts, journeys, constraints, roles, locales, proximity bands, and evidence language. Use after architecture design and before contamination or semantic QA.