Main Navigation Docs CLI Reference

Appearance

Sidebar Navigation

Getting Started

Getting Inference

Configuring GitHub

Per-Org Mode

Operations

Agents

Triage

Code

Review

Fix

Retro

Prioritize

User Guides

Bugfix Workflow

Customizing Agents

Customizing with AGENTS.md

Customizing with Skills

Building Custom Agents

Running Agents Locally

Concepts

Vision

Architecture

Runtimes

Glossary

Infrastructure

Infrastructure Reference

Mint Administration

Standalone Mint

Private Repositories

Distributed Tracing

Advanced Setup

Contributing

Development

CLI Internals

E2E Testing

Testing Workflows

Roadmap

Landscape

Architecture Decisions

NUMBER. TITLE

1. Use ADRs for decision making

2. Initial Fullsend Design

3. Org-level configuration lives in a conventional repo

4. Go as the implementation language for core tooling

5. Forge abstraction layer

6. Ordered layer model for install, uninstall, and analyze

7. Per-role GitHub Apps with manifest-based creation

8. workflow_dispatch for cross-repo agent dispatch

9. Use pull_request_target in shim workflows

10. Stored browser session for e2e authentication in CI

11. Canonical schema for admin-managed org config.yaml (v1)

12. Normative v1 Git-tracked files under `.fullsend` for admin install

13. Admin install: repository enrollment v1

14. Admin install: GitHub Apps and `.fullsend` credential surface (v1)

15. Normative implementation contracts live under docs/normative/

16. Unidirectional control flow through the execution stack

17. Credential Isolation for Sandboxed Agents

18. Scripted pipeline for multi-agent orchestration

19. Web source under web/ and Cloudflare project under cloudflare_site/

20. Composable single-responsibility agents with individual sandboxes

21. JSONL reasoning trace exposure from sandboxed agents

22. Harness-level output schema enforcement

23. User documentation structure

24. Harness definitions and shared directory layout

25. Provider-based credential delivery for sandboxed agents

26. Stage-based dispatch for agent workflow decoupling

27. Allowed and Disallowed Tools for Agents

28. GitLab Support Architecture

29. Central token mint and shared apps for a secretless .fullsend

30. OpenShell sandbox interaction model

31. Reusable workflows for action-installed distribution

32. safe-push wrapper binary for sandboxed agents

33. Per-repo installation mode

34. Centralized shim routing via dispatch.yml

35. Layered content resolution

36. Agent Execution Sandbox Architecture

38. Universal harness access via URLs and paths

39. TOTP automation for e2e 2FA

40. Org pool for parallel e2e tests

41. Synchronous workflow_call for event-driven agent dispatch

42. Use /fs- prefix for all slash commands

43. Add upstream source headers to managed scaffold files

44. Deprecate per-org installation mode

45. Forge-portable harness schema

46. Host-side API server design for sandboxed agents

47. Vendored installs with --vendor

48. Automatic Updates

49. Agent configuration environment variable convention

50. Framework-native distributed tracing with OpenTelemetry

47. agent-eval-harness for test infrastructure

48. Functional tests for agent pipelines

53. Agent-driven branch targeting for the code agent

54. Require authorization on all agent dispatch paths

55. Unified environment variable delivery for harness runner and sandbox

56. Per-repo pre-commit tools registry

57. Repos management for per-repo installations

58. Agent registration

59. Public mint mode with wildcard allowlists

60. Cross-org mint authorization via org variables

61. Harness CEL triggers and fullsend dispatch drivers

62. Resolving per-repo dispatch version skew

64. Deprecate customized/ directory overlay

Design Documents

Adaptive Agent Selection

Agent Architecture

Agent-Compatible Code

Agent Infrastructure

Applied Problem Considerations

Architectural Invariants

Autonomy Spectrum

Code Review

Codebase Context

Contribution Volume

Contributor Guidance

Cross-Run Memory

Debugging Agentic Workflows

Downstream/Upstream

GitLab Support Implementation Details

Governance

Human Factors

Intent Representation

MCP Configuration Drift

Operational Observability

Performance and Load Impact Verification

Platform Nativeness

Production Feedback

Repo Readiness

Security Threat Model

Testing the Agents

Tool Call Risk Assessment

Experiments (Exploratory)

NNNN. TITLE

1. Agent outage fire drill

2. Claude-based ADR drift scanner

3. ADR-0046 drift scanner

4. Zero-config autonomous bug fix engine with self-improving meta-loop

5. Agent scoped tools triage

6. Code agent evaluation

7. GitHub Actions agent runtime MVP

8. Guardrails evaluation

9. Hermes-inspired security patterns

10. Host-side API server for sandboxed agents

11. Integration Service design doc drift analysis

12. Model Armor vs AI agent triage

13. OpenShell policy bypass

14. OpenShell sandbox evaluation

15. Prompt injection defense-in-depth

16. Promptfoo for agent evaluation in CI

17. Reasoning monitor agent for prompt injection detection

18. Runner hello world

19. Skills

20. Target repository skills in triage

21. Tool scoping

22. Claude GitHub App auth

23. Review cache publication policy

NNNN. Short description

CLAUDE.md

Doc Site

Web Admin (On Hold)

Internals

Admin OAuth Worker

Specifications

Design: Fullsend admin installation SPA (static, GitHub App–centric)

Design: Documentation site on Cloudflare Workers (static assets, PR previews, fork-safe CI)

Design: Wire the Installer to Lay Down Agent Runtime Content

Enrollment Reconciliation Design

UX design: Fullsend admin SPA (screens, states, and errors)

Design: Admin org list from GitHub App installations (browser-first)

Concise proposal title

OpenShell Native Sandbox Transport

Silent skip for unconfigured roles in dispatch workflows

Behavioral Thresholds for Functional Tests

Review Agent: Contextual Labels via issue-labels Skill

Triage Agent Prerequisites Action

Autonomy Readiness Skill Design

Implementation Plans

Documentation site → Cloudflare Workers (fork-safe CI) Implementation Plan

Fullsend admin installation SPA Implementation Plan

Admin org list from GitHub App installations — Implementation Plan

Retro Agent Implementation Plan

OpenShell Native Sandbox Transport Implementation Plan

Silent Skip Unconfigured Roles — Implementation Plan

Review Agent Contextual Labels Implementation Plan

Triage Prerequisites Action Implementation Plan

Autonomy Readiness Skill Implementation Plan

Unified Env Var Delivery Implementation Plan

ADR-0046 Drift Scanner Implementation Plan

Implementation Plan: ADR-0045 Forge-Portable Harness Schema — Phase 1

Implementation Plan: ADR-0045 Forge-Portable Harness Schema — Phase 2 (Adopt)

Implementation Plan: ADR-0045 Forge-Portable Harness Schema — Phase 3 (Deprecate)

Implementation Plan: ADR-0045 Forge-Portable Harness Schema — Phase 4 (Remove)

Agent Execution Environment

Implementation plan: Agent registration

Design Document: Automatic Updates

Implementation Plan: Deprecate customized/ directory overlay (ADR-0064)

Implementation Plan: Deprecate Per-Org Installation Mode (ADR-0044)

ADR 62: Inline stages into reusable-dispatch.yml (per-repo only)

Implementation Plan: `fullsend repos init`

Implementation Plan: Repos Management for Per-Repo Installations

Implementation Plan: ADR-0038 Universal Harness Access via URLs

Implementation Plan: Phase 2 — Transitive Dependency Resolution

Implementation Plan: Phase 3 — Lock Files

Implementation Plan: Phase 4 — Runtime Dependency Loading

Universal Harness Access

Plan: Inference Provider Credential Provisioning (Vertex AI)

On this page

19. Skills

Experiments with skill authoring and consumption patterns.

Edit this page on GitHub

Pager

Previous page18. Runner hello world

Next page20. Target repository skills in triage

19. Skills ​

19. Skills