agentleFS
ceilf6ceilf6/FrontAgent/CLAUDE.md

FrontAgent

CLAUDE.md124 starsChanged 5 months agoMITView on GitHub

When documents conflict or expected behavior is unclear, ask the maintainer instead of silently choosing a new architecture. For non-trivial repository changes, use this loop: FrontAgent uses an open-source maintainer workflow. Do not add training-camp claim comments, score labels, progress ledgers, timeout-close automation, or comment-triggered auto-merge rules unless maintainers explicitly request a separate workflow. This project is indexed by GitNexus as FrontAgent (6641 symbols, 13666 relationships, 300 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and…

The file

Show its rules and text

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

19 rules. About 0 are common, 8 are distinctive, and 11 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 11

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When documents conflict or expected behavior is unclear, ask the maintainer instead of silently choosing a new architecture.

    line 11
  2. Very specific:

    Run pnpm agent:bootstrap and pnpm quality:predev before code changes when feasible.

    line 15
  3. Distinctive:

    Before editing a function, class, or method, run GitNexus impact analysis and report the blast radius.

    line 16
  4. Distinctive:

    Keep changes focused and independently reviewable.

    line 17
  5. Distinctive:

    Run focused tests for the touched area, then broader gates as risk increases.

    line 18
  6. Very specific:

    Before final review, run pnpm quality:precommit at minimum and use GitNexus detect_changes to inspect the final diff.

    line 19
  7. Distinctive:

    Start from an Issue, Discussion, or maintainer-approved task description.

    line 26
  8. Very specific:

    Create a short-lived branch from develop using feat/, fix/, docs/, or chore/.

    line 27
  9. Very specific:

    Run pnpm agent:bootstrap and pnpm quality:predev.

    line 28
  10. Very specific:

    Run pnpm quality:local before pushing when feasible.

    line 30
  11. Distinctive:

    Wait for GitHub Actions, Contract Guard, Repo Guard, Codex, Copilot, and maintainer review comments.

    line 32
  12. Very specific:

    MUST run impact analysis before editing any symbol: Before modifying a function, class, or method, run gitnexus_impact({target: …

    line 49
  13. Distinctive:

    MUST warn the user: if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.

    line 51
  14. Very specific:

    When exploring unfamiliar code, use gitnexus_query({query: "concept"}) to find execution flows instead of grepping.

    line 52
  15. Very specific:

    When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use gitnexus_context({name: …

    line 53
  16. Very specific:

    NEVER edit a function, class, or method without first running gitnexus_impact on it.

    line 57
  17. Distinctive:

    NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.

    line 58
  18. Very specific:

    NEVER rename symbols with find-and-replace — use gitnexus_rename which understands the call graph.

    line 59
  19. Very specific:

    NEVER commit changes without running gitnexus_detect_changes() to check affected scope.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

FrontAgent OSS Harness

Documents

  1. README.md is the public product and command overview.
  2. docs/architecture.md and docs/design.md define architecture and SDD behavior.
  3. CONTRIBUTING.md, docs/workflow.md, and docs/knowledge-contract.md define OSS contribution, Harness, and GitNexus contract rules.
  4. Issue or PR text defines the specific change request.
  5. Existing code is evidence, but it does not override the documents above.

When documents conflict or expected behavior is unclear, ask the maintainer instead of silently choosing a new architecture.

Work

  1. Run pnpm agent:bootstrap and pnpm quality:predev before code changes when feasible.
  2. Before editing a function, class, or method, run GitNexus impact analysis and report the blast radius.
  3. Keep changes focused and independently reviewable.
  4. Run focused tests for the touched area, then broader gates as risk increases.
  5. Before final review, run pnpm quality:precommit at minimum and use GitNexus detect_changes to inspect the final diff.
  6. For critical skeleton changes, fill the PR GitNexus impact summary with concrete detect_changes plus query, context, or impact results.

Harness Loop

For non-trivial repository changes, use this loop:

  1. Start from an Issue, Discussion, or maintainer-approved task description.
  2. Create a short-lived branch from develop using feat/, fix/, docs/, or chore/.
  3. Run pnpm agent:bootstrap and pnpm quality:predev.
  4. Implement the smallest reviewable change with focused tests.
  5. Run pnpm quality:local before pushing when feasible.
  6. Open a PR to develop with the PR template filled in, including the GitNexus impact summary for critical skeleton changes.
  7. Wait for GitHub Actions, Contract Guard, Repo Guard, Codex, Copilot, and maintainer review comments.
  8. Address actionable review comments with follow-up commits, then rerun the relevant gates.
  9. Let maintainers decide merge readiness; do not add comment-triggered auto-merge behavior.

OSS Scope

FrontAgent uses an open-source maintainer workflow. Do not add training-camp claim comments, score labels, progress ledgers, timeout-close automation, or comment-triggered auto-merge rules unless maintainers explicitly request a separate workflow.

<!-- gitnexus:start -->

GitNexus — Code Intelligence

This project is indexed by GitNexus as FrontAgent (6641 symbols, 13666 relationships, 300 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.

If any GitNexus tool warns the index is stale, run npx gitnexus analyze in terminal first.

Always Do

  • MUST run impact analysis before editing any symbol. Before modifying a function, class, or method, run gitnexus_impact({target: "symbolName", direction: "upstream"}) and report the blast radius (direct callers, affected processes, risk level) to the user.
  • MUST run gitnexus_detect_changes() before committing to verify your changes only affect expected symbols and execution flows.
  • MUST warn the user if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
  • When exploring unfamiliar code, use gitnexus_query({query: "concept"}) to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.
  • When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use gitnexus_context({name: "symbolName"}).

Never Do

  • NEVER edit a function, class, or method without first running gitnexus_impact on it.
  • NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
  • NEVER rename symbols with find-and-replace — use gitnexus_rename which understands the call graph.
  • NEVER commit changes without running gitnexus_detect_changes() to check affected scope.

Resources

ResourceUse for
gitnexus://repo/FrontAgent/contextCodebase overview, check index freshness
gitnexus://repo/FrontAgent/clustersAll functional areas
gitnexus://repo/FrontAgent/processesAll execution flows
gitnexus://repo/FrontAgent/process/{name}Step-by-step execution trace

CLI

TaskRead this skill file
Understand architecture / "How does X work?".claude/skills/gitnexus/gitnexus-exploring/SKILL.md
Blast radius / "What breaks if I change X?".claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md
Trace bugs / "Why is X failing?".claude/skills/gitnexus/gitnexus-debugging/SKILL.md
Rename / extract / split / refactor.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md
Tools, resources, schema reference.claude/skills/gitnexus/gitnexus-guide/SKILL.md
Index, status, clean, wiki CLI commands.claude/skills/gitnexus/gitnexus-cli/SKILL.md
<!-- gitnexus:end -->

Download now (ZIP)

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.