A two-agent approval process for decisions that would normally require a human, such as deploying, changing live systems, pushing code, or cleaning up. Both agents must independently agree that the written approval rules allow the action.

Use it when a sprint has explicitly authorized two trusted agents to decide whether a specific human approval gate may be passed.

It prevents one agent from making a sensitive decision alone or treating uncertainty as permission. If either agent disagrees or cannot confirm the decision, the action remains blocked.

How dazzaji/interlateral_agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. 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/dazzaji/interlateral_agents/main/.agent/skills/gate-keeper/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dazzaji/interlateral_agents

Made for: Claude Code, Codex.

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/dazzaji/interlateral_agents/gate-keeper/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/gate-keeper)

Your own site

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/gate-keeper"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/gate-keeper/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/dazzaji/interlateral_agents/gate-keeper"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/gate-keeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,234 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	$0.00064	$0.04234
Opus 5.5	$0.00026	$0.01694
Sonnet 5.5	$0.00013	$0.00847
Haiku 4.5	$0.00006	$0.00423

Measured 1mo ago against content hash add4fac60692, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gate-keeper 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 1mo 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.

.agent/skills/gate-keeper/SKILL.md · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gate Keeper

Compatibility: two live agents with direct comms, preferably Claude Opus plus Codex.

Purpose

Use this skill when an autonomous sprint would otherwise stop at a human approval gate, and the human principal has explicitly authorized two trusted proxy agents to decide whether that exact gate should be approved.

The gate keepers do not implement sprint work. They represent the principal's written approval standard.

Approval requires unanimous consensus:

Both gate keepers independently conclude:
"Based on the delegation authority, written approval policy, preference profile, and evidence packet, the principal would approve this gate."

If both approve, they issue a scoped, verifiable approval token. If either denies, is uncertain, times out, or cannot reaffirm, the gate is not approved and the sprint team receives concrete fixes, resubmission requirements, or an escalation.

Required Inputs

All inputs come from the prompt, sprint spec, or gate request packet.

principal: human whose judgment is being represented, for example Principal Human
gate: exact gate token requested, for example GO DEPLOY PILOT
delegation_authority: path or quoted human instruction proving the principal authorized this proxy council for this gate or gate family
request_id: stable id for this gate request, including sprint/run id and attempt number
requester_identity: lead/commander/session identity authorized by the sprint to submit the request
approval_policy: written standards the proxies must apply
policy_revision: path and hash/revision of the approval policy used for this decision
preference_profile: optional human guidance, risk tolerances, recurring preferences, and gate-specific defaults
preference_revision: path and hash/revision of the preference profile, or none
evidence_packet: paths to evidence, diffs, logs, gate reports, and relevant terminal/session names
evidence_revision: evidence manifest path plus hash/revision at decision time
sprint_file: sprint source-of-truth document
requesting_team: lead/quartet session or artifact path requesting approval
approval_expiry: mandatory expiry or invalidation condition
proxy_conflicts: statement of whether either proxy served as lead, implementer, reviewer, breaker, verifier, overseer, or requester for the work being approved
decision_log: optional prior decisions for this principal with short rationale

Read the full file on GitHub · 538 lines

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.

1mo ago First seen · 538 lines · 64 tokens per session scan A add4fac60692

Subscribe to this mod's changes

gate-keeper is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 64 tokens to every session and 4,234 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.

Building agents

gate-keeper next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gate-keeperdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	64	Claude Code, Codex
imagegenopenai/codex	Skill	133k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

interlateral_agents: Skill for Claude Code