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 radiantlogicinc/fastworkflow --skill author-planning-commandsgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote 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/radiantlogicinc/fastworkflow/author-planning-commands)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/author-planning-commands"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/author-planning-commands/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/radiantlogicinc/fastworkflow/author-planning-commands"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/author-planning-commands.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 | $0.00271 | $0.11225 |
| Opus 5.5 | $0.00108 | $0.04490 |
| Sonnet 5.5 | $0.00054 | $0.02245 |
| Haiku 4.5 | $0.00027 | $0.01123 |
Grade A, and why
author-planning-commands 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 — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing planning commands
A planning command is one Python file, _commands/<name>.py, or _commands/<Context>/<name>.py for
a planning command of a context (named <Context>/<name>). It is written like a command file: its
Signature describes a job and its Input declares the job's typed arguments, exactly as a
command's does. Where a command has a ResponseGenerator, a planning command has a top-level
PlanGenerator: each public method is a phase that returns its steps as text.
How a matched planning command runs (workflow_agent.match_planning_command matches it;
planning_commands.typed_planning_call fills it):
- A planning command is a label of the classifiers whose scope holds it, trained from its
plain_utterances, so a request can reach it as it reaches an execution command. WithJEV_API_KEYthe matcher picks the planning command for a sub-task from its description andplain_utterancesfirst. Without the key the planner finds the command in its list, and no typed call fills its inputs. - The planner fills
Inputin one typed call. - The arguments are checked:
check_argumentschecks each field against its type and its options (copied_from_command_texthere), and the file's own rules run. - A refused call is filled once more with the refusal in view. A second refusal is asked of the user as a question when the turn may ask; otherwise the text planner takes over.
- The call's phases run, and the steps they return become the agent's plan. Code runs the steps it can (see the step grammar below).
There is no separate planning step in front of a matched call and no fast path around it.
The one-page guide is docs/planning_command_file_layout.md in the fastWorkflow repository (not in
the wheel), with the preview; docs/planning_command_phases.md covers phases, facts, code-run steps
and answers. The module documentation of fastworkflow.planning (the form),
fastworkflow.planning_commands and fastworkflow.planning_phases (the runtime) ships with the
package and is the source of truth.
Code references below name a module of the fastworkflow package and a symbol in it.
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 First seen · 574 lines · 271 tokens per session scan A b2a6fa719839
author-planning-commands is a skill published in the GitHub repository radiantlogicinc/fastworkflow (54 stars, last pushed yesterday), licensed Apache-2.0. It adds 271 tokens to every session and 11,225 once invoked, about $0.0011 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 2026-11-12.
author-planning-commands compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| author-planning-commandsradiantlogicinc/fastworkflow | Skill | 54 | yesterday | Apache-2.0 | A | 271 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 6d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |