agentleFS
AgenticPawanAgenticPawan/FullStack-Pilot/.codex/AGENTS.md

FullStack-Pilot

AGENTS.md2 starsChanged 4 months agoMITView on GitHub

Minimal Codex-compatible config for the AgenticPawan/FullStack-Pilot plugin. Full agent definitions, skill load maps, and routing rules live in AGENTS.md at the repo root. This plugin governs Angular, .NET/ASP.NET Core, SQL Server/EF Core, and Azure/Bicep projects. All commands are prefixed fsp-. All agents are prefixed @<stack>- or @fsp-. Before reading source files for documentation or API surface questions, use: 1. microsoftdocssearch — quick structured lookup in official docs 2. microsoftcodesamplesearch — official code examples 3. microsoftdocs_fetch — full page fetch when…

  • Deletes or force-pushes
  • Commits and pushes

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All commands are prefixed fsp-.

    line 9
  2. Distinctive:

    Before reading source files for documentation or API surface questions, use:

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

FullStack Pilot — Codex Agent Config

Minimal Codex-compatible config for the AgenticPawan/FullStack-Pilot plugin. Full agent definitions, skill load maps, and routing rules live in AGENTS.md at the repo root.

Stack Coverage

This plugin governs Angular, .NET/ASP.NET Core, SQL Server/EF Core, and Azure/Bicep projects. All commands are prefixed fsp-. All agents are prefixed @<stack>- or @fsp-.

Agent Roster (by intent)

When you need to…Route to
Review a multi-layer diff@fullstack-reviewer
Fix after a multi-layer review@fullstack-implementor
Triage a production symptom@fullstack-support
Write an Angular component or service@angular-implementor
Review Angular/TypeScript diff@angular-reviewer
Debug a browser or RxJS issue@angular-support
Write or fix C#/ASP.NET Core code@dotnet-implementor
Review .NET diff@dotnet-reviewer
Debug an API or startup exception@dotnet-support
Write an EF Core migration or query@sql-implementor
Review a migration or schema diff@sql-reviewer
Debug a slow query or deadlock@sql-support
Write or fix Bicep / GitHub Actions@infra-implementor
Review infrastructure diff@infra-reviewer
Debug a deployment or scaling issue@infra-support
Turn a feature ask into a spec@fsp-analyst
Design or assess architecture@fsp-architect
Scout a codebase region cheaply@fsp-scout
Run QA against acceptance criteria@fsp-qa

Core Skills (loaded by agents automatically)

  • pilot-core:stack-detection — identifies which stacks are present
  • pilot-core:project-instincts — three-tier learning (instincts / corrections / discoveries)
  • pilot-core:session-handoff — writes .claude/handoff.md at session end
  • pilot-core:quality-gate — 7-phase build/test/security/migration gate
  • pilot-core:stack-health — A–F graded health report (6 dimensions)
  • pilot-core:convention-learner — captures codebase-specific conventions
  • pilot-core:mcp-discovery — surfaces relevant MCP tools for the task

Key Commands

CommandPurpose
/fsp-initDetect stacks, write stack-profile.json, scaffold baseline
/fsp-bootstrapScaffold governance baselines before feature work
/fsp-auditRun security and governance audit
/fsp-fixApply remediation from audit findings
/fsp-learnCapture conventions into knowledge/conventions.md
/fsp-buildFull 8-step build pipeline (analyst → architect → implement → QA)
/fsp-architectArchitecture assessment or planning only
/fsp-verify7-phase quality gate before PR
/fsp-healthA–F graded stack health report
/fsp-checkpointSave session state and write handoff note

Hard Rules (enforced by hooks in pilot-core)

  1. No hardcoded secrets — blocked at write time by secret-guard.js
  2. No dangerous SQL/Azure patterns — blocked by dangerous-patterns.js
  3. No git push --force or git reset --hard — blocked by bash-guard.js
  4. No new HttpClient(), async void, DateTime.Now — warned by antipattern-guard.js
  5. No Angular [innerHTML] without DomSanitizer — blocked via dangerous-patterns.json
  6. Autonomous loops capped at 10 iterations — agent must write .claude/loop-stopped.md and stop

MCP-First Principle

Before reading source files for documentation or API surface questions, use:

  1. microsoft_docs_search — quick structured lookup in official docs
  2. microsoft_code_sample_search — official code examples
  3. microsoft_docs_fetch — full page fetch when search is insufficient

Pipeline Artifacts

Agents hand off via files under .claude/pilot/ — never by pasting content into chat:

PathWritten by
.claude/pilot/stack-profile.json@fsp-init / stack-detection skill
.claude/pilot/context/<scope>.md@fsp-scout
.claude/pilot/specs/<feature>.md@fsp-analyst
.claude/pilot/architecture/ASSESSMENT.md@fsp-architect
.claude/pilot/builds/<feature>/PLAN.md@fsp-architect plan mode
.claude/pilot/builds/<feature>/QA-REPORT.md@fsp-qa
.claude/pilot/audit/findings.json/fsp-audit
.claude/handoff.mdsession-handoff skill / /fsp-checkpoint

Knowledge Base

  • plugins/pilot-core/knowledge/stack-antipatterns.md — multi-stack antipatterns (ANG-, NET-, SQL-, AZR-)
  • plugins/pilot-core/knowledge/stack-packages.md — vetted packages for all stacks
  • plugins/pilot-core/knowledge/decisions/ — ADRs (ADR-001 through ADR-005)
  • .claude/pilot/knowledge/conventions.md — project-specific conventions captured by /fsp-learn

Install

/plugin marketplace add AgenticPawan/FullStack-Pilot

See AGENTS.md at the repo root for full routing logic, model assignments, and conflict resolution rules.

Download now (ZIP)

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.