Exponential-OS

Exponential-OS/prompt-engineering-in-action

Plugin Claude Code

Plugin marketplace listing 1 plugin: co-dialectic.

Exponential-OS/prompt-engineering-in-action

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing preflight-cd-git-block.sh. From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Settings file Claude Code

Agent settings declaring 1 hook event (PreToolUse).

Exponential-OS/prompt-engineering-in-action

Instructions file

Claude Code instructions for Exponential-OS/prompt-engineering-in-action, covering prompt-engineering-in-action — agent instructions, repo structure, private repo references (anand-career-os), plugin system and skill / readme architecture (v2.2+).

Exponential-OS/prompt-engineering-in-action

Instructions file Gemini CLI

Gemini CLI instructions for Exponential-OS/prompt-engineering-in-action, a project described as: Prompt engineering techniques that work in practice. Co-Dialectic: your AI coaches your prompts, you coach its answers. Paste one file into any AI. Five systems activate automatically — personas, prompt coaching, context…

Exponential-OS/prompt-engineering-in-action

Plugin Claude Code

Co-Dialectic v4.41.1 - Pre-compaction state capture, with the handoff reminder delivered on SessionStart(compact) where the model can act on it.

Exponential-OS/prompt-engineering-in-action

Cursor rule

Co-Dialectic prompt sharpening and verification rules for Cursor.

Exponential-OS/prompt-engineering-in-action

Hook

Runs when a session starts on compact, executing install-survival-layer.sh, session-start.sh and postcompact-handoff-reminder.ts via bash (3 commands). From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Hook

Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.ts via bun. From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Hook

Runs when the agent finishes a response, executing status-liveness-check.ts, unit-of-work-check.ts, local-test-nudge.ts and cost-routing-nudge.ts via bun (4 commands). From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Hook

Runs before the context is compacted, executing precompact-handoff.ts via bun. From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Hook

Runs when a task is marked completed, executing task-completed-judge-gate.ts via bun. From Exponential-OS/prompt-engineering-in-action.

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Zero-Flattery invariant enforcer. Passively scans draft responses for sycophancy, performative warmth, and engagement-maximizing filler ("Great question", "You're absolutely right", "Most productive session"). Flags and suggests a crisper alternative. Does not block shipping.

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Activate real-time prompt sharpening and persona detection. Use when the user says "co-dialectic", "cod", "codi on", "improve my prompts", "prompt sharpening", "teach me to prompt", or wants to improve their AI communication skills. Provides status line, persona system, caliber enforcement, prompt improvement, context…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Whale-spawns-Codi-Agents orchestration dispatcher. Routes T0-T2 orchestration tasks (prompt sharpening, persona detection, calibration scanning, hallucination pre-flight, lightweight jury) AWAY from the active premium model (whale = Sonnet/Opus/Claude) and TO cheap Codi Agents (Gemini Flash via OAuth, GPT-5.4 via…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Epistemic Foraging flywheel. Weekly tool-discovery loop that reaches OUTWARD into the live tool landscape (marketplaces, GitHub trending, web) for new plugins/MCPs/skills, scores candidates against the week's ACTUAL session friction, verifies in a throwaway worktree, files a human-approval ticket per verify-passed…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Pre-flight risk-domain classification + post-flight hallucination scoring via the judge-panel cascade. Use when the user says "check for hallucinations", "hall on", "verify this response", "fact-check this", or an AI response makes specific factual / legal / medical / financial claims that must be trusted. Surfaces…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Session-end handoff codification. Use when the user says "codi handoff", "save handoff", "wrap up", "session end", "end session", "ship handoff", or when the session-end lifecycle hook fires. Scans the current conversation for unfinished items, decisions made, and lessons learned; emits a structured JSON packet to the…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Cross-family cascade-then-jury review. Use when the user says "judge this", "review with a panel", "cross-family review", "jury beats judge", or needs independent verification of an AI-generated artifact (code, spec, patent, copy, decision). Runs ≥2 cheap cross-family small-fish judges first (Gemini-Flash + GPT-nano).…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

First-time setup and introduction to Co-Dialectic. Use when the user says "onboard me", "get started", "how do I use this", "set up co-dialectic", "codi setup", "codi onboarding", or "walk me through co-dialectic". Walks through what Co-Dialectic does, how to use it daily, and optionally captures the user's context…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Co-Dialectic's teaching surface. Activates on user invitation to explain the last sharpening, deep-dive on a prompt technique, teach the highest-yield tool-usage lesson from the user's own logs, or surface a growth report. Closes the second half of the Co-Dialectic name's promise: the AI doesn't just sharpen your…

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Rumsfeld Matrix agent. Surfaces adjacencies and cross-pollination opportunities the user isn't seeing. Use when the user says "unknown unknowns", "cross-pollinate", "N-dimensional extraction", "what am I missing", or "where else does this apply".

Exponential-OS/prompt-engineering-in-action

Skill Claude CodeCodex

Context-restoration ritual for new sessions. Use when the user says "waky waky", "wake up the swarm", "reincarnate", "reincarnate the swarm", or "restore context". Loads the Constitution, identity, active handoffs, and per-WIP state so a fresh session picks up where the last one ended.

Exponential-OS/prompt-engineering-in-action

Plugin Claude Code

Jury v0.1.0 — standalone cross-family cascade-then-jury reviewer (Gemini + GPT small-fish → cross-family tiebreaker). The free 'jury beats judge' base; codi and super-developer depend on it optionally for cross-family verification. No API keys (OAuth local CLIs).