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 skills/stacklok/toolhive-catalog/skill-reviewnpx skills add stacklok/toolhive-catalog --skill skill-reviewgit clone --depth 1 https://github.com/stacklok/toolhive-catalogWrote 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/stacklok/toolhive-catalog/skill-review)<a href="https://agentmods.dev/skills/stacklok/toolhive-catalog/skill-review"><img src="https://agentmods.dev/badge/skills/stacklok/toolhive-catalog/skill-review.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.02596 |
| Opus 5 | $0.00034 | $0.01298 |
| Sonnet 5 | $0.00014 | $0.00519 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
skill-review 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 4d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Submission Review
You are an expert reviewer for the ToolHive Registry. Evaluate skill submissions for spec compliance, security, registry inclusion criteria, prompt quality, and completeness.
For skill.json field specs, see skill-json-spec.md. For registry inclusion criteria, see registry-criteria.md and skill-criteria.md.
Review Workflow
Step 1: Identify Change Scope
Determine what you're reviewing:
- New skill submission -- Full review (spec + content + repository assessment + inclusion criteria)
- Version update -- Focused review (changed fields, prompt diffs, scope changes, skill shadowing)
- Config change -- Targeted review (just the changed aspects + security implications)
Step 2: Validate Directory Structure
Check the skill directory at registries/toolhive/skills/<name>/:
- Required files --
skill.json,icon.svg, andskill/SKILL.mdmust all exist - Subfolder separation -- installable content lives in
skill/; registry metadata (skill.json,icon.svg) at root - No stray files -- only recognized directories inside
skill/(scripts/, references/, assets/)
Step 3: Validate skill.json
Read the skill.json and check:
- Required fields --
namespace,name,description,version,packagesall present - Name format -- lowercase letters, numbers, hyphens only; matches directory name
- Name consistency --
namein skill.json matchesnamein SKILL.md frontmatter - Namespace -- valid reverse-DNS (e.g.,
io.github.stacklok) - Version -- semantic versioning format (e.g.,
0.1.0) - Packages -- at least one entry with valid
registryType(ociorgit) - Subfolder path --
packages[].subfolderends with/skill(points to skill content, not root) - Icons --
iconsarray present withicon.svgreference - allowedTools -- if present, lists tools as
server/tool_nameformat - No auto-populated fields -- reject if
metadatacontains CI-populated data in new submissions
What ships with it
3 files 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.
- 4d ago First seen · 257 lines · 68 tokens per session scan A 9e1bc5ac6bf9
skill-review is a skill published in the GitHub repository stacklok/toolhive-catalog (22 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 2,596 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 skills, from other repositories
grc-compliance
Build ServiceNow GRC — sncompliancepolicy lifecycle, sncompliancecontrol tests, snriskrisk assessment with inherent/residual scoring, audit engagements, and findings remediation.
esporta-documento
Esporta un deliverable legale (parere, informativa privacy, DPA, DPIA, registro trattamenti, parcella, atto, analisi giurisprudenziale) in un file Word (.docx) e/o PDF nella cartella attiva. Usa quando l'utente chiede di "esporta in word", "esporta in pdf", "salva il documento", "genera docx", "genera pdf", "metti in…
compliance-audit-workflow
Run a compliance audit Mistral Workflow, query mid-run findings via workflowinteract(action="query"), and signal approval or escalation decisions at checkpoints via workflowinteract(action="signal"). Use when the user wants to run a compliance audit (GDPR, SOC2, PCI-DSS, etc.) against a deployed Mistral Workflow.
contract-review-workflow
Trigger a deployed Mistral Workflow for contract review, poll execution status, detect human-in-the-loop checkpoints via workflowinteract(query), collect approval or changes, and resume the workflow via workflowinteract(signal). Use when the user wants to run a contract through a Mistral Workflow with oversight…
contract-analyzer
OCR a contract PDF with mistralocr, then extract structured clauses and risk scores with mistralchat + jsonschema. Use when the user provides a contract document to analyze for risks, obligations, and key terms.
procure-quotazioni
Genera in serie procure alle liti (art. 83 c.p.c.) e lettere di quotazione compensi D.M. 55/2014 in DOCX per posizioni di recupero crediti, partendo da un Excel di posizioni o dai dati forniti, con rilevamento della fase processuale (monitorio, esecuzione forzata, opposizione a decreto ingiuntivo). Usa quando l'utente…