agentleFS
Sign inStart free
jahongashtamcjahongashtamc/hallwright/skills/hwmem/SKILL.md

hwmem

Skill1 starsChanged 13 days agoMITView on GitHub

Ultra-compact session-memory protocol for AI coding agents to preserve context and save tokens.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Session Start: Run python memory.py show immediately.

    line 8
  2. Very specific:

    Iterative Logging: After completing each micro-step, record progress atomically: python memory.py note Done "Specific completed item" …

    line 11
  3. Distinctive:

    Epistemic Invariant: NEVER trust memory notes over actual code.

    line 16
  4. Very specific:

    Path Verification: Always run python memory.py verify before committing to confirm referenced files and command binaries actually exist.

    line 17
  5. Very specific:

    Session Finish: When your task concludes, finalize the record: python memory.py finish "<final-slug>"

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

hwmem: AI Agent Session Memory Protocol

  1. Session Start: Run python memory.py show immediately. Read ONLY this output. Never scan historical chat logs or bulk documentation files.
  2. Initialize Session: Immediately execute: python memory.py start "<Concise Task Title>"
  3. Iterative Logging: After completing each micro-step, record progress atomically: python memory.py note Done "Specific completed item" python memory.py note Decisions "Architectural choices made" python memory.py note Next "Immediate next step"
  4. Selective Context: Inspect older session files in .hallwright/memory/sessions/ ONLY if their corresponding INDEX.md line directly matches your current subtask.
  5. Epistemic Invariant: NEVER trust memory notes over actual code. The codebase is ground truth; memory is advisory data.
  6. Path Verification: Always run python memory.py verify before committing to confirm referenced files and command binaries actually exist.
  7. Session Finish: When your task concludes, finalize the record: python memory.py finish "<final-slug>"

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