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/organvm-iv-taxis/a-i--skillsWrote 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/organvm-iv-taxis/a-i--skills/plan-workflow)<a href="https://agentmods.dev/commands/organvm-iv-taxis/a-i--skills/plan-workflow"><img src="https://agentmods.dev/badge/commands/organvm-iv-taxis/a-i--skills/plan-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/organvm-iv-taxis/a-i--skills/plan-workflow"><img src="https://agentmods.dev/badge/commands/organvm-iv-taxis/a-i--skills/plan-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 | $0.00024 | $0.00303 |
| Opus 5 | $0.00012 | $0.00151 |
| Sonnet 5 | $0.00005 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
plan-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 11d 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.
What it actually says
/plan-workflow
Generate an ordered skill chain to accomplish a goal.
Usage
/plan-workflow <goal description>
Example: /plan-workflow Build a secure REST API with tests and deployment
Process
- Read
distributions/skills-registry.jsonto load all skill metadata - Match the goal against skill descriptions, tags, and triggers
- Build a dependency chain based on input/output compatibility
- Include complementary skills that enhance the workflow
- Present the plan as an ordered list with data flow
Output Format
Goal: <user's goal>
Skill Chain:
1. skill-name (category)
Inputs: what it needs
Outputs: what it produces
Purpose: why it's in the chain
2. skill-name (category)
...
Data Flow:
service-requirements -> [api-design-patterns] -> api-specification
api-specification -> [backend-implementation-patterns] -> backend-code
...
Also Consider:
- complementary-skill: brief description
Notes
- Plans are suggestions; approve or modify before executing
- Use
/skill-healthto check individual skills before running a chain - Chains are limited to 8 skills for reviewability
- Prefer core-tier skills when multiple options match
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.
- 11d ago First seen · 53 lines · 24 tokens per session scan A 3a689b260a71
plan-workflow is a command published in the GitHub repository organvm-iv-taxis/a-i--skills (17 stars, last pushed 14d ago), licensed Apache-2.0. It adds 24 tokens to every session and 303 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 commands, from other repositories
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
brainstorm-divergent
Generate genuinely different ideas across the solution space, then converge on the strongest few.
design-diagram
Specify a technical diagram that answers one question at one level of abstraction.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
animal-friendship
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/animal-friendship/SKILL.md.
planar-binding
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/planar-binding/SKILL.md.