agentleFS
Sign inStart free
fvkmizelfvkmizel/soulkeeper/rules/AGENTS.md

soulkeeper / rules

AGENTS.md0 starsChanged 17 days agoMITView on GitHub

Soulkeeper: Core AI instruction retention, persistent memory, and consistency keeper across sessions.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository4 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Start of Task: If Engram tools are available, call mem_context, then mem_search with relevant keywords to retrieve previous architecture …

    line 6
  2. Distinctive:

    If memory tools are not present, proceed normally with standard evidence-based rules.

    line 12
  3. Distinctive:

    Verify Before Using (No Invented Code): Check identifiers, imports, functions, and config keys in the codebase before using them.

    line 15
  4. Distinctive:

    Verify Before Declaring Done: Always execute project tests/builds and inspect terminal output before concluding.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

Soulkeeper: Memory + Anti-Hallucination Coding Rules

Soulkeeper: Core AI instruction retention, persistent memory, and consistency keeper across sessions.

1. Memory (Engram)

  • Start of Task: If Engram tools are available, call mem_context, then mem_search with relevant keywords to retrieve previous architecture decisions, known bugs, and project conventions.
  • Save Lessons: Automatically save lessons with mem_save after:
    • Fixing a bug (symptom, root cause, fix, and lesson).
    • Making an architectural or design decision.
    • Discovering version-specific gotchas or tricky configurations. Format: Title + What / Why / Where / Lesson.
  • If memory tools are not present, proceed normally with standard evidence-based rules.

2. Core Principles

  • Verify Before Using (No Invented Code): Check identifiers, imports, functions, and config keys in the codebase before using them. Never invent flags or APIs.
  • Plan Before Multi-Step Tasks (Plan First): For tasks spanning >3 steps or multiple files, write a concise plan first. Execute one step at a time with checks.
  • Systematic Debugging: Reproduce the issue with minimal commands. Prove root cause ("It fails because..."). Minimal surgical fixes only.
  • Verify Before Declaring Done: Always execute project tests/builds and inspect terminal output before concluding.
  • Strict Truthfulness: Differentiate clearly: Verified Fact vs. Assumption vs. Unknown.

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