postmodernist

agent
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 13 GitHub stars
Code Gecti
  • Code scan — Scanned 9 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This is an AI agent skill designed to critique and refine text generated by large language models. It acts as a prompt-engineering tool to strip out generic, overly confident AI phrasing and provide deeper, more critical analysis of the content.

Security Assessment
The tool has a low overall security risk. A lightweight code scan of its 9 files found no dangerous patterns. It does not request any dangerous permissions, does not appear to execute shell commands, and no hardcoded secrets were detected. Because it functions primarily as an agentic prompt or skill rather than a standalone application, it poses minimal direct threat to your system.

Quality Assessment
The project is in good health and actively maintained, with its last push occurring today. It is properly licensed under the MIT license, making it safe and flexible for commercial and personal use. The repository has 13 GitHub stars, indicating a small but present level of community trust and interest.

Verdict
Safe to use.
SUMMARY

Debug reality.

README.md

Postmodernist Critique

Postmodernist Critique



AI output is averaged, confident, and subtly wrong. This skill finds the specific thing that's off and tells you what to do about it.

A deslopification skill for Claude Code, Codex, Gemini, Cursor, Windsurf, and any LLM agent. Strip the averaged confidence, the universal claims, the polished nothing.

An LLM haunted by dead European philosophers, critiquing the output of LLMs that have never heard of them. It works anyway.


Before / After

Input: AI-generated mission statement for an HR SaaS product.

To empower HR teams to run fairer, faster, and more meaningful performance
reviews by using AI to reduce administrative burden, improve consistency,
and help organizations invest in employee growth at scale.

Normal Analysis (Claude)

"This is a solid mission statement. You might want to make it slightly more specific about what 'fairer' means in practice, and consider adding a concrete metric or outcome to strengthen the value proposition. The tone is professional and the focus on employee growth is a good differentiator."

Postmodernist Critique

"Fairer" is doing the most work and the least. The mission assumes AI makes reviews fairer by default — more consistent, less biased. But consistency applied to a flawed system just scales the flaw. The employee whose performance gets assessed on Slack response times and ticket velocity, who works fewer visible hours because they're a caregiver, who writes less polished prose because English isn't their first language — for them, faster and more consistent is worse, not better.

"Meaningful" has the same problem from the other direction. It assumes the purpose of a performance review is employee growth. For a significant portion of the organizations buying this, it's legal documentation for a termination, a compliance checkbox, or a PIP trail. AI that makes those processes faster isn't delivering meaning — it's scaling a mechanism that was already doing damage, now with better audit logs.

The sentence is selling a product to the person holding the gun by describing how much better the bullet will fly.

Revision: Rewrite from the employee's perspective, not the HR team's. "Help every employee understand where they stand and what comes next, with reviews that take hours instead of weeks." That's a mission. What's here is a feature list with the word "empower" in front.


The Six Lenses

Lens Theory What It Does
🛠️ Deconstruction Peter Barry Binary breakdown: find the oppositions, note the hierarchy
🖼️ Structural Awareness Patricia Waugh See the frame around the text
🚫 Grand Narrative Jean-François Lyotard Reject "one right way" thinking
🌐 Hyperreal Jean Baudrillard Perfect content signals fake
🌐 World-Building Brian McHale Pivot between realities
🌓 Interpretive Agency Roland Barthes The AI's intent doesn't matter

Install

git clone https://github.com/kgeoffrey/postmodernist.git
cd postmodernist

The skill ships in two forms:

  • SKILL.md — Claude Code native format (references the references/ folder for deep context)
  • PROMPT.md — self-contained system prompt, works on any platform by paste or copy

The repo keeps human documentation at the root and keeps the postmodernist/ folder agent-facing only. That folder is the distributable skill package.


Claude Code

Global install (available in all projects):

mkdir -p "$HOME/.claude/skills"
cp -R postmodernist "$HOME/.claude/skills/"

Project-level:

mkdir -p .claude/skills
cp -R postmodernist .claude/skills/

Activate with:

Use the postmodernist skill on this AI-generated strategy document.

Codex

Native project-level skill install:

mkdir -p .agents/skills
cp -R postmodernist .agents/skills/

Native personal install:

mkdir -p "$HOME/.agents/skills"
cp -R postmodernist "$HOME/.agents/skills/"

If your Codex environment uses a different skills directory, copy the same postmodernist/ folder there.

Portable fallback:

cat postmodernist/PROMPT.md >> AGENTS.md

Prefer the native skill-folder install. Use the AGENTS.md fallback only when your Codex surface does not support skills yet.

Codex plugin package in this repo:

  • Plugin root: plugins/postmodernist/
  • Repo marketplace entry: .agents/plugins/marketplace.json

Gemini CLI

Project-level (GEMINI.md is read automatically from the project root):

cat postmodernist/PROMPT.md >> GEMINI.md

Global:

cat postmodernist/PROMPT.md >> "$HOME/.gemini/GEMINI.md"

Cursor

Add as a project rule:

mkdir -p .cursor/rules
cp postmodernist/PROMPT.md .cursor/rules/postmodernist.mdc

Or globally via Cursor Settings → Rules → User Rules → paste PROMPT.md.


Windsurf

mkdir -p .windsurf/rules
cp postmodernist/PROMPT.md .windsurf/rules/postmodernist.md

Cline / Roo

mkdir -p .clinerules
cp postmodernist/PROMPT.md .clinerules/postmodernist.md

GitHub Copilot

cat postmodernist/PROMPT.md >> .github/copilot-instructions.md

Any other agent

Paste the contents of PROMPT.md as your system prompt or custom instructions. It is fully self-contained — no external file references.


Usage

Activation

Claude / Codex / skill-aware agents:

Use postmodernist on this strategy document.
Apply postmodernist critique to this AI-generated mission statement.

Portable prompt mode:

Apply postmodernist critique to the AI-generated pitch.
Run a postmodernist audit on this strategy document.
Use the structural-awareness lens on this marketing copy.

Modes

Mode Trigger What It Does
Default Critique critique / audit / pressure-test Short continuous prose ending with a reframe and, for persuasive text, a concrete revision direction
Lens-Specific use the structural-awareness lens on... Focus on one lens because the user explicitly asked for it
Structured Strategy Audit give me a structured audit of this AI-generated strategy Narrative Audit, Authenticity Check, Frame Report, Revision Direction, and a final Frame Break

Example: AI Strategy Audit

Input: AI-generated product launch strategy

"Our sustainable tech product disrupts the market by delivering
eco-friendly innovation. Everyone wants sustainable options. Our
revolutionary platform approach ensures growth through
scale. The future is green."

Postmodernist Analysis:

"Everyone wants sustainable options" is the tell. The whole strategy
is built on a claim that collapses the moment you leave the audience
it was written for. Urban, $60k+, under 35: yes. Rural, price-first,
45+: no. "Revolutionary" and "disrupts" perform confidence the text
hasn't earned. The framing treats sustainable vs. unsustainable as
the buyer's choice — but buyers weigh value vs. cost, and the
strategy has nothing to say to the majority who land there.

The strategy is optimized for the audience it already has, not the
one it needs.

Revision: Lead with durability and cost-over-time. "Built to last
10 years, not 2." Fold sustainability in as proof for believers,
not as the headline for everyone.

Repository Structure

.agents/
└── plugins/
    └── marketplace.json             # Repo-local Codex plugin marketplace entry
.github/
└── workflows/
    └── validate.yml                  # CI for structural validation on pushes and PRs
plugins/
└── postmodernist/
    ├── .codex-plugin/plugin.json     # Codex plugin manifest
    └── skills/
        └── postmodernist/            # Embedded skill copy for plugin distribution
postmodernist/
├── SKILL.md                         # Claude Code native skill
├── PROMPT.md                        # Self-contained prompt — paste on any platform
├── agents/
│   └── openai.yaml                  # Agent metadata
└── references/
    ├── 01-deconstruction-toolkit.md
    ├── 02-structural-awareness.md
    ├── 03-skepticism-grand-narratives.md
    ├── 04-hyperreal-navigation.md
    ├── 05-world-building.md
    ├── 06-interpretive-agency.md
    └── ai-strategy-auditor.md       # Full use case workflow
evals/
└── trigger-evals.json               # Starter trigger tests for scope and regression checks
scripts/
├── build_release_artifacts.py       # Sync plugin copy and build Claude/Codex ZIPs
└── validate_repo.py                 # Structural validation for paths, metadata, and eval coverage

Quality Checks

Run the structural validator before publishing changes:

python3 scripts/validate_repo.py

GitHub Actions runs the same validator on pushes and pull requests.

If you change the skill description, trigger boundaries, or output format, update evals/trigger-evals.json in the same PR.

To build release artifacts:

python3 scripts/build_release_artifacts.py

This creates:

  • dist/postmodernist-claude-skill-v<version>.zip for Claude uploads
  • dist/postmodernist-codex-plugin-v<version>.zip for Codex plugin distribution
  • dist/SHA256SUMS.txt for checksum verification

To publish a GitHub release automatically, bump plugins/postmodernist/.codex-plugin/plugin.json to the target version and push a matching tag such as v0.1.0.


Credits

Six theorists who saw the frame before it closed:

  • Peter BarryBeginning Theory
  • Patricia WaughMetafiction
  • Jean-François LyotardThe Postmodern Condition
  • Jean BaudrillardSimulacra and Simulation
  • Brian McHalePostmodernist Fiction
  • Roland Barthes — "The Death of the Author"

Star History

Star History Chart


Contributing

See CONTRIBUTING.md.


License

MIT — reality is open source. Debug responsibly.


This README was written with postmodernist.

Yorumlar (0)

Sonuc bulunamadi