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/bengous/claude-code-pluginsWrote 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/commands/bengous/claude-code-plugins/explain-workflow)<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/explain-workflow"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/explain-workflow/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/commands/bengous/claude-code-plugins/explain-workflow"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/explain-workflow.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 | $0.00017 | $0.01709 |
| Opus 5.5 | $0.00007 | $0.00684 |
| Sonnet 5.5 | $0.00003 | $0.00342 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
explain-workflow 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 yesterday.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Trace
Target: $ARGUMENTS
Your Task
Trace the complete execution flow of the target and produce ASCII workflow diagrams showing every step from user input to final output.
What the target is and why it exists are out of scope: the trace shows what happens, step by step, when it executes.
Step 1: Resolve the Target
Determine what kind of target was provided:
Plugin component (command, skill, agent, hook):
- Search for matching
.mdfiles in commands/, skills/, agents/, hooks/ directories across all plugins - Find files by name:
**/commands/$ARGUMENTS.md,**/commands/$ARGUMENTS/*.md,**/skills/$ARGUMENTS/SKILL.md,**/agents/$ARGUMENTS.md - If target contains
:, split on:asplugin:component. The plugin part is thenamein a.claude-plugin/plugin.json, which can differ from its directory (e.g.,claude-orchestration:orc->orchestration/commands/orc.md)
File path:
- If target contains
/or ends in.md,.sh,.py,.ts,.js, treat as a direct file path and Read it - The file may be a command, skill, agent definition, OR a plan/design document that describes a Claude Code agent workflow
- In all cases, extract the Claude Code components (commands, skills, agents, tools, hooks) described or referenced in the file
Workflow description:
- If neither above matches, Grep the codebase for relevant keywords
- Identify the primary entry point(s) that match the description
Step 2: Trace the Execution Path
Starting from the resolved file(s), systematically trace the Claude Code agent workflow.
If the target is a plan or design document that describes an agent workflow (rather than being an executable command/skill itself): extract the Claude Code components it references -- commands invoked, agents spawned, skills used, tools called, hooks involved -- then trace each component by reading its source file. The plan describes the intended flow; the component files contain the actual implementation to trace.
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.
- yesterday Changed f32ec4774ee0
- 26d ago Changed · +1 lines b68c80fb8e1e
- 27d ago Changed · -2 lines 39c9ce5f1c75
- 1mo ago First seen · 176 lines · 17 tokens per session scan A 4bfe4897f125
explain-workflow is a command published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,709 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
spec-research
A requirements-research command that turns a request into a set of constraints and checkable success criteria. It explores the relevant parts of a project in parallel and creates a structured proposal.
triage
Triage Linear issue with comprehensive analysis.
land
Resolve and squash merge one named, currently authorized pull request.
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.