A framework for collaboration between Codex, Claude, and Gemini, three different AI models.

Use it to check the framework, run a shared task, pass a release gate, or inspect the run status. It is invoked with the /triparty command or its equivalent.

It coordinates reviews and cross-checks so a task can be examined by multiple models before the result is merged and checked.

How r-design-j/tri-party-framework configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to r-design-j/tri-party-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/r-design-j/tri-party-framework/main/.claude/skills/triparty/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/r-design-j/tri-party-framework

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/r-design-j/tri-party-framework/triparty/github.svg)](https://agentmods.dev/skills/r-design-j/tri-party-framework/triparty)

Your own site

<a href="https://agentmods.dev/skills/r-design-j/tri-party-framework/triparty"><img src="https://agentmods.dev/badge/skills/r-design-j/tri-party-framework/triparty/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/r-design-j/tri-party-framework/triparty"><img src="https://agentmods.dev/badge/skills/r-design-j/tri-party-framework/triparty.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 525 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.00525
Opus 5	$0.00042	$0.00262
Sonnet 5	$0.00017	$0.00105
Haiku 4.5	$0.00008	$0.00052

Measured 9d ago against content hash bc5fab1163bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

triparty scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/triparty/SKILL.md · 42 lines

What it actually says

Triparty

Use the existing portable framework. Do not recreate the protocol by writing new ad hoc Markdown files.

Arguments from the slash command:

$ARGUMENTS

Resolution

Prefer triparty from PATH when command -v triparty succeeds.
Otherwise read ~/.triparty-framework/config and use $TRIPARTY_FRAMEWORK_HOME/scripts/triparty.sh.
Otherwise, if the current repository has scripts/triparty.sh, use that script.
If none are available, report that the framework is not installed or not discoverable, and ask whether to clone https://github.com/r-design-j/tri-party-framework.

Dispatch

No arguments or status: run triparty status.
preflight: run triparty preflight.
run <task>: run triparty run "<task>"; this portable core path performs preflight, independent reviews, mutual cross-audit, merge, and state validation.
release-gate <run-dir>: run triparty release-gate <run-dir>.
Any other non-empty arguments: treat the full argument string as the task and run triparty run "$ARGUMENTS".

Reporting

Report the run directory, source status, and whether the result is true_triparty_ready or partial. Do not call a result tri-party-backed unless the merge gate and state validation pass. For public release or publishing claims, also run triparty release-gate <run-dir>.

Adapter Boundaries

Do not call claude, gemini, or provider APIs directly from this slash layer.
Do not provide or emulate --skip-cross-audit, --skip-merge, or any other bypass.
Do not assert readiness in the slash layer; read readiness from the portable core's state.json through triparty status or triparty release-gate.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 42 lines · 84 tokens per session scan A bc5fab1163bb

Subscribe to this mod's changes

triparty is a skill published in the GitHub repository r-design-j/tri-party-framework (4 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 525 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents agent-framework ai-agents claude codex developer-tools gemini

setup-background-job

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.

andresharpe/dotbot · 22 tokens

auto-improve

GAN-style iterative improvement loop for any text artifact. Mutates a file, grades each change against a rubric with a SEPARATE model, keeps only verified wins (pairwise-judged), reverts the rest. The git history is the improvement log. Use when the user wants to autonomously improve the quality of a document, email…

crimeacs/auto-improve · 87 tokens

blazor-component-design

Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.

andresharpe/dotbot · 53 tokens

create-migration

Create and manage Entity Framework Core database migrations including schema changes, seed data, and rollback strategies. Use when adding or modifying EF Core entities, setting up a new DbContext, applying data seeding, running dotnet ef commands, or troubleshooting migration conflicts.

andresharpe/dotbot · 55 tokens

verify

Run all verification gates (privacy scan, git cleanliness, git pushed) and report results.

andresharpe/dotbot · 20 tokens

squads-learn

Capture learnings after completing work. Use when finishing a task, fixing a bug, discovering a pattern, or learning something worth remembering for future sessions. Helps build institutional memory.

agents-squads/squads-cli · 41 tokens

tri-party-framework: Skill for Claude Code