This page is the complete reference for all 17 protocols in the AI Protocol Kit, organized by the failure mode they address. Each lane groups protocols that share a common problem class — the kind of work that breaks down in predictable ways when the AI has no explicit behavioral contract. Find the lane that matches your situation, then pick the protocol closest to the specific failure you want to prevent.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/xxyoudeadpunkxx/ai-protocol-kit/llms.txt
Use this file to discover all available pages before exploring further.
Shape the Work
Use these protocols when the task is ambiguous, premature, overloaded, or underspecified. This is the failure mode where AI collapses fuzzy input into a confident answer before the real constraints, structure, or success criteria are visible. The protocols in this lane force shaping before synthesis — they keep the AI in an exploration and constraint-extraction mode until the structure is stable enough for execution.Idea Shaping Protocol v1
Turn a rough idea into a clear, constraint-tested structure before asking AI to write, plan, design, or build anything. Operates in explicit ALIGNMENT and DRAFTING modes with a required gate between them.
Pre-Task Expansion Protocol v1
Stop the AI from collapsing too quickly into the obvious answer by exposing alternative readings, tensions, and the surrounding shape of the problem before any output is produced.
Structural Shaping Protocol v1
Shape ambiguous input into operational form before synthesis, with gates, evidence level, source boundaries, and artifact direction made explicit before drafting begins.
System Reading Protocol v0.2
Read the gap between declared intent and observable behavior to extract the operative principle of a system — without premature solutions or invented explanations.
Brief the Artifact
Use these protocols when the AI needs a clear brief before writing, building, or structuring output. Without a brief, AI defaults to a generic format that fits no particular reader, platform, or purpose. These protocols close the brief before anything is drafted.Output for Real Readers Protocol v2
Write guides, README text, emails, pages, forms, instructions, or any reader-facing material with reader, purpose, tone, constraints, and language closed before drafting begins.
HTML Page & Tool Briefing Protocol v2
Guide an AI from raw intake to a complete implementation brief for a static HTML page, web surface, or local tool — before a single line of markup is written.
Review Findings and Evidence
Use these protocols when the job is inspection, bugs, uncertainty, evidence, or claim control. Findings collapse when evidence and inference get mixed together — these protocols keep them structurally separate.Field Findings & Bugs Protocol v2
Capture findings and bugs as structured artifacts while keeping evidence, inference, uncertainty, relations, and later promotion explicitly separated. Prevents confident-sounding summaries from burying what was actually observed.
System Reading Protocol v0.2
Read the gap between declared intent and observable behavior to extract the operative principle of a system — without premature solutions or invented explanations.
Reasoning, Constraints & System Reading
Use these protocols when the task needs expansion, system interpretation, or constraint-aware reasoning before output. These are the cases that are not just unclear — they are structurally easy to misread, over-simplify, or resolve with a flat compromise that hides the dominant force.Pre-Task Expansion Protocol v1
Expose alternative readings, tensions, and surrounding shape before committing to an answer. Prevents the AI from over-fitting to the first plausible interpretation.
System Reading Protocol v0.2
Extract the operative principle of a system by reading what it actually does — not what it claims to do. Useful when declared intent and observable behavior diverge.
PHI-Lens Protocol v4.a
Handle non-trivial tasks where constraints interact and a flat compromise would hide the dominant force, counterforce, or asymmetry. Uses an internal lens and coupling model to structure constraint interaction before output.
GitHub / Public Repo & Page Publishing
Use these protocols when the work touches GitHub, Pages, README files, public pages, discovery files, badges, or publication hygiene. GitHub publication has its own class of failure modes — wrong paths, missing metadata, incorrect discovery files, premature pushes, and README copy that performs rather than informs.GitHub Repository Publication Preparation Protocol v2
Prepare a repository for clean GitHub publication, with project classification, workspace and risk audit, minimal file decisions, GitHub feature choices, and explicit confirmation before commits, remotes, Pages, or push.
GitHub README Framing and Authoring Protocol v2
Write or restructure a GitHub repository README from repository evidence, reader fit, and the real job the README must perform — not from a generic template.
GitHub Pages Discovery Set Protocol v1
Prepare GitHub Pages user, org, or project sites with correct publication roots, discovery files, canonical URLs, sitemap, robots handling, and low-noise machine-readable footer links — without breaking GitHub Pages path rules.
GitHub Badge, Telemetry & Counter Protocol v1.2.3
Decide which badges, counters, analytics, traffic checks, or validation checks make sense for a GitHub repo or GitHub Page — without adding vanity widgets that track nothing real.
Public Page Publication Protocol v2
Prepare, restructure, or publish a public page, landing page, showcase, portfolio page, documentation entrypoint, or GitHub Pages site with page role, audience, metadata, accessibility, links, visual identity, and publication risks closed before deploy or push.
HTML and Website Discovery Set Protocol v1.2
Prepare static HTML pages or websites with machine-readable discovery files, head metadata, canonical URLs, sitemap, robots rules, and low-noise footer links for correct indexing and discoverability.
Govern Agentic Sessions
Use these protocols when the AI must operate with tools, files, repo state, review loops, or multi-pass control. This is the failure mode where AI acts without adequate behavioral rails — approving its own work, inventing file contents, treating chat summaries as repository truth, or failing to maintain a coherent execution state across multiple steps.GPT Agentic Posture Contract
Make ChatGPT work more like Codex: tool-aware, grounded in real files and artifacts, ledger-based, verification-oriented, and willing to stop when the task is not ready.
Triad AI Orchestration Protocol v3
Run a review loop between an executing AI near the real target and a reviewing AI over snapshots, repo state, diffs, or files — while preserving target authority and patch evidence. Requires the human as the only bridge between the two AI actors.
PHI-Lens Protocol v4.a
Handle complex, constraint-heavy sessions where the active lenses and borders need explicit coupling to prevent flat compromise outputs. Also used as a reasoning governor in agentic contexts.
Some protocols appear in more than one lane. That is intentional. System Reading Protocol v0.2, for example, is useful both when shaping ambiguous work and when doing constraint-aware reasoning — because the underlying job (reading real behavior instead of declared intent) is the same in both contexts. PHI-Lens Protocol v4.a similarly spans reasoning and agentic session governance. The lane a protocol appears in does not limit where it can be used — it describes the failure modes it was built to address.