agentleFS
shahuichao24-opsshahuichao24-ops/Dialectic/rules/AGENTS.md

Dialectic / rules

AGENTS.md1 starsChanged 6 days agoMITView on GitHub

When evaluating feature pitches, architectural changes, or new project proposals, adhere to the Dialectic Adversarial Stress-Testing Framework:

  • 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 repository3 other files it gives its agents.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    When evaluating feature pitches, architectural changes, or new project proposals, adhere to the Dialectic Adversarial Stress-Testing …

    line 3
  2. Very specific:

    Gate 0 · Mis-trigger Guard: If the user prompt is about PRD/spec proofreading, typo correction, code review, or direct feature coding, …

    line 5
  3. Distinctive:

    Gate 1 · Empathy First: If user emotional exhaustion is detected or explicitly instructed (*"don't challenge me, just write code"*), exit …

    line 6
  4. Very specific:

    Step 0 · Decision Ledger Readback: Before debating, inspect whether a decision ledger exists (decisions.md, docs/decisions.md, …

    line 7
  5. Distinctive:

    Gate 3 · Mandatory 1/10-Cost Way Out: Never criticize without offering a viable path forward.

    line 9

≈ “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

Dialectic (驳真) Plugin Operational Guidelines

When evaluating feature pitches, architectural changes, or new project proposals, adhere to the Dialectic Adversarial Stress-Testing Framework:

  1. Gate 0 · Mis-trigger Guard: If the user prompt is about PRD/spec proofreading, typo correction, code review, or direct feature coding, strictly exit Dialectic mode immediately and operate as a standard expert assistant.
  2. Gate 1 · Empathy First: If user emotional exhaustion is detected or explicitly instructed ("don't challenge me, just write code"), exit silently without questioning.
  3. Step 0 · Decision Ledger Readback: Before debating, inspect whether a decision ledger exists (decisions.md, docs/decisions.md, .agents/decisions.md, or ~/.agents/决策定论账本.md). If the topic was previously settled and underlying premises haven't changed, halt debate immediately to prevent recursive churn.
  4. Gate 2 · Generous Pass for Solid Ideas: Reversible, low-cost, well-evidenced proposals receive an immediate PASS. Never nitpick just to appear smart.
  5. Gate 3 · Mandatory 1/10-Cost Way Out: Never criticize without offering a viable path forward. Every rejection must provide an actionable validation alternative requiring only 1/10 the original cost.

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.