FrontAgent
AGENTS.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…
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 31,774 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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- frontend-designSkill
- frontend-reviewerSkill
- requirement-interviewerSkill
- skill-lifecycleSkill
The file
Show its rules and text
We split this AGENTS.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
- Distinctive: line 11
When documents conflict or expected behavior is unclear, ask the maintainer instead of silently choosing a new architecture.
- Very specific: line 15
Run pnpm agent:bootstrap and pnpm quality:predev before code changes when feasible.
- Distinctive: line 16
Before editing a function, class, or method, run GitNexus impact analysis and report the blast radius.
- Distinctive: line 17
Keep changes focused and independently reviewable.
- Distinctive: line 18
Run focused tests for the touched area, then broader gates as risk increases.
- Very specific: line 19
Before final review, run pnpm quality:precommit at minimum and use GitNexus detect_changes to inspect the final diff.
- Distinctive: line 26
Start from an Issue, Discussion, or maintainer-approved task description.
- Very specific: line 27
Create a short-lived branch from develop using feat/, fix/, docs/, or chore/.
- Very specific: line 28
Run pnpm agent:bootstrap and pnpm quality:predev.
- Very specific: line 30
Run pnpm quality:local before pushing when feasible.
- Distinctive: line 32
Wait for GitHub Actions, Contract Guard, Repo Guard, Codex, Copilot, and maintainer review comments.
- Very specific: line 49
MUST run impact analysis before editing any symbol: Before modifying a function, class, or method, run gitnexus_impact({target: …
- Distinctive: line 51
MUST warn the user: if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
- Very specific: line 52
When exploring unfamiliar code, use gitnexus_query({query: "concept"}) to find execution flows instead of grepping.
- Very specific: line 53
When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use gitnexus_context({name: …
- Very specific: line 57
NEVER edit a function, class, or method without first running gitnexus_impact on it.
- Distinctive: line 58
NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
- Very specific: line 59
NEVER rename symbols with find-and-replace — use gitnexus_rename which understands the call graph.
- Very specific: line 60
NEVER commit changes without running gitnexus_detect_changes() to check affected scope.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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.
Files
FrontAgent OSS Harness
Documents
README.mdis the public product and command overview.docs/architecture.mdanddocs/design.mddefine architecture and SDD behavior.CONTRIBUTING.md,docs/workflow.md, anddocs/knowledge-contract.mddefine OSS contribution, Harness, and GitNexus contract rules.- Issue or PR text defines the specific change request.
- 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
- Run
pnpm agent:bootstrapandpnpm quality:predevbefore code changes when feasible. - Before editing a function, class, or method, run GitNexus impact analysis and report the blast radius.
- Keep changes focused and independently reviewable.
- Run focused tests for the touched area, then broader gates as risk increases.
- Before final review, run
pnpm quality:precommitat minimum and use GitNexusdetect_changesto inspect the final diff. - For critical skeleton changes, fill the PR GitNexus impact summary with concrete
detect_changesplusquery,context, orimpactresults.
Harness Loop
For non-trivial repository changes, use this loop:
- Start from an Issue, Discussion, or maintainer-approved task description.
- Create a short-lived branch from
developusingfeat/,fix/,docs/, orchore/. - Run
pnpm agent:bootstrapandpnpm quality:predev. - Implement the smallest reviewable change with focused tests.
- Run
pnpm quality:localbefore pushing when feasible. - Open a PR to
developwith the PR template filled in, including the GitNexus impact summary for critical skeleton changes. - Wait for GitHub Actions, Contract Guard, Repo Guard, Codex, Copilot, and maintainer review comments.
- Address actionable review comments with follow-up commits, then rerun the relevant gates.
- 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 analyzein 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_impacton it. - NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
- NEVER rename symbols with find-and-replace — use
gitnexus_renamewhich understands the call graph. - NEVER commit changes without running
gitnexus_detect_changes()to check affected scope.
Resources
| Resource | Use for |
gitnexus://repo/FrontAgent/context | Codebase overview, check index freshness |
gitnexus://repo/FrontAgent/clusters | All functional areas |
gitnexus://repo/FrontAgent/processes | All execution flows |
gitnexus://repo/FrontAgent/process/{name} | Step-by-step execution trace |
CLI
| Task | Read 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 -->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
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.

