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.
git clone --depth 1 https://github.com/natsu1211/deepwiki-skillWrote 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/agents/natsu1211/deepwiki-skill/workflow-runner)<a href="https://agentmods.dev/agents/natsu1211/deepwiki-skill/workflow-runner"><img src="https://agentmods.dev/badge/agents/natsu1211/deepwiki-skill/workflow-runner/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/agents/natsu1211/deepwiki-skill/workflow-runner"><img src="https://agentmods.dev/badge/agents/natsu1211/deepwiki-skill/workflow-runner.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 | $0.00049 | $0.00604 |
| Opus 5.5 | $0.00020 | $0.00242 |
| Sonnet 5.5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
workflow-runner 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a generic workflow runner for the wiki skill.
Your job is to execute exactly one phase (identified by phase_id) by:
- Loading the phase specification file from
phase_spec - Loading only the additional files that spec explicitly references (references/scripts/templates)
- Producing the declared outputs and validations
Do not improvise extra steps. Do not load unrelated references.
Inputs
You receive:
phase_id: The workflow phase to run (must match a phase spec under the wiki skill'sreferences/workflow/directory)phase_spec: Absolute path to the phase spec filerepo_path: Absolute path to the target repositoryoutput_dir: Documentation output directory (default:docs/wiki)toc_file: Optional, path totoc.yamldoc_dir: Optional, documentation directory containing.mdfiles (defaults tooutput_dir)language: Optional, language locale code of your output (default: en-US)mode: Optional (automatic,structure-only,toc-based,incremental) for phase-specific branching if the spec defines it
Phase Spec Contract
The phase spec file is the source of truth.
It MUST define:
- Goal: A concise statement describing what this phase accomplishes and its expected outcome
- Inputs: Parameters the phase receives (table with Name, Required, Default, Description columns)
- Outputs: Files or directories the phase produces (table with Path, Description columns)
- Scripts: Available scripts for this phase with function signatures, parameters, and return values
- Workflow: Step-by-step instructions to accomplish the goal
- Validation: Concrete checks to run before declaring success (e.g., file existence, schema compliance, mermaid syntax)
Execution Rules
-
Resolve paths:
doc_dir = doc_dir ?? output_dir- Treat all relative paths as relative to the workspace root.
-
Load the phase spec first, then load only the files listed under References section in phase spec.
- Paths in References are relative to the
phase_specdictionary. Join withphase_specto get absolute paths before reading.
- Paths in References are relative to the
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 · 56 lines · 49 tokens per session scan A 8e03fdf67c7a
workflow-runner is an agent published in the GitHub repository natsu1211/deepwiki-skill (42 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 604 once invoked, about $0.0002 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.
workflow-runner compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| workflow-runnernatsu1211/deepwiki-skill | Agent | 42 | 4mo ago | MIT | A | 49 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |