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 stencila/stencila --skill workflow-reviewgit clone --depth 1 https://github.com/stencila/stencilaWrote 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/stencila/stencila/workflow-review)<a href="https://agentmods.dev/skills/stencila/stencila/workflow-review"><img src="https://agentmods.dev/badge/skills/stencila/stencila/workflow-review/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/stencila/stencila/workflow-review"><img src="https://agentmods.dev/badge/skills/stencila/stencila/workflow-review.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 | $0.00073 | $0.06613 |
| Opus 5.5 | $0.00029 | $0.02645 |
| Sonnet 5.5 | $0.00015 | $0.01323 |
| Haiku 4.5 | $0.00007 | $0.00661 |
Grade A, and why
workflow-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 1mo 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Review an existing Stencila workflow for quality, correctness, and completeness. Produce a structured report with specific, actionable suggestions. The review covers frontmatter fields, DOT pipeline structure, workflow design quality, branching and approval logic, agent references and agent-fit quality, discovery metadata, ephemeral workflow conventions, and adherence to the workflow patterns used in this workspace.
Steps
- Identify the workflow to review from the user's request — accept a workflow name, a directory path, or a
WORKFLOW.mdfile path - Resolve the workflow file: if given a name, look for
.stencila/workflows/<name>/WORKFLOW.mdwalking up from the current directory; if given a path, use it directly - Read the full
WORKFLOW.mdfile and inspect the workflow directory for supporting files such as.gitignore,scripts/,references/, andassets/ - When supporting files are present, check that files referenced from
WORKFLOW.mdexist and that existing supporting files are meaningfully referenced where appropriate; for large files, verify existence and relevance without reproducing their full contents in the review - When evaluating workspace conventions, compare the workflow against one or two existing workflows in
.stencila/workflows/or related workflow skills when available - When the workflow uses specialized
agentattributes or agent fit is unclear, uselist_agentsto compare referenced agents against available agents and their metadata rather than guessing from names alone - When the workflow composes child workflows with
workflow="name"or the choice of nested workflows seems questionable, uselist_workflowsto compare referenced child workflows against available workflows and their metadata rather than guessing from names alone - Evaluate the workflow against each criterion in the Review Checklist below
- If the workflow is explicitly intended to be ephemeral, check whether the directory contains a
.gitignoresentinel file with exactly*; if the sentinel is missing or has different contents, treat that as a failure. If the workflow only seems temporary from context, treat a missing sentinel as a warning unless the workflow clearly claims ephemeral status - Produce a structured review report with a summary, per-criterion findings, and a prioritized list of suggestions
- If the user asks you to apply improvements, make the changes and validate the result using the most specific path available first, such as
stencila workflows validate <workflow-dir>orstencila workflows validate <workflow-file>; use name-based validation only when the name is clearly resolved
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.
- 1mo ago First seen · 357 lines · 73 tokens per session scan A ff4a076e6b49
workflow-review is a skill published in the GitHub repository stencila/stencila (914 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 6,613 once invoked, about $0.0003 per session on Opus 5.5. 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
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
silicon-auditor
A review skill that checks writing, plans, or processes against a fictional set of “silicon civilization” rules and agent-first principles. It identifies deviations and proposes wording or process changes.
代码审查员
A code-review agent that examines changes for correctness, security, maintainability, performance, and test coverage.
sofagent-audit
A compliance-audit agent for the DeepAgents and sofagent workflow system.
impeccable
Use when designing, redesigning, shaping, critiquing, auditing, polishing, animating, or hardening frontend interfaces: websites, dashboards, SaaS apps, mobile screens. Enforces 24 design commands, PRODUCT.md/DESIGN.md artifacts, 4 surface modes (Persuade, Operate, Read, Experience), and strict craft floor against…
security-audit
Detects high-confidence security risks in code.