agentleFS
Sign inStart free
patrickbdevaneypatrickbdevaney/hermes-max/skills/workflow-plan-first/SKILL.md

workflow-plan-first

Skill1 starsChanged 6 months agoMITView on GitHub

ALWAYS run first on any task touching more than one file or more than ~3 steps.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the plan to a file (PLAN.md in the project) so it survives context compression.

    line 22
  2. Distinctive:

    Only then begin subtask 1.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- TRIGGERS WHEN: ALWAYS run first on any task touching more than one file or more than ~3 steps. -->

Plan first — never start coding a multi-step task without a written plan.

  1. Restate the goal in one sentence and the DEFINITION OF DONE as a concrete, testable checklist (e.g. "endpoint returns 200 with JSON {ok:true}", "pytest passes", "file X exists").
  2. Query codebase-rag (mcp_hermes_max_codebase_rag_search_code) and knowledge-graph (mcp_hermes_max_knowledge_graph_recall_about) for relevant existing code, patterns, and prior decisions BEFORE planning. Plan around what exists; don't invent.
  3. Decompose into the SMALLEST subtasks that are each independently verifiable. Each subtask = one bounded change you could verify with a single test or check. Aim for steps a junior dev could do in 10 minutes. Write them as a todo/kanban list.
  4. PRE-MORTEM the plan (lookahead): for each subtask, ask "what is the most likely way this step hangs, errors, or produces something untestable?" Common traps: long-running processes (see process-gotchas), missing deps, wrong working dir, a step with no way to verify it. Adjust the plan to make every step verifiable and non-hanging.
  5. Write the plan to a file (PLAN.md in the project) so it survives context compression. Re-read PLAN.md at the start of each subtask. The plan is the source of truth, not memory.
  6. Only then begin subtask 1.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free