nanolang
CLAUDE.md628 starsChanged 4 months agoApache-2.0View on GitHub
I follow AGENTS.md and the portable skills in skills/. GitHub Issues is my only project task ledger. I track all new and resumed project work in GitHub Issues. GitHub Issues is my task ledger; docs/ROADMAP.md remains my ordered product contract and evidence index. I do not use MAC, bd/beads, or local TODO files as an alternative task ledger. Historical MAC IDs remain provenance only. I search before creating an issue, record branch/file ownership in an issue comment, and link commits,…
- Commits and pushes
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
If GitHub is unavailable, I preserve my work and report the unfiled issue.
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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.
Files
I follow AGENTS.md and the portable skills in skills/. GitHub Issues is my
only project task ledger.
Issue Tracking
I track all new and resumed project work in GitHub Issues.
GitHub Issues is my task ledger; docs/ROADMAP.md remains my ordered product
contract and evidence index. I do not use MAC, bd/beads, or local TODO files as
an alternative task ledger. Historical MAC IDs remain provenance only.
gh issue list --repo jordanhubbard/nanolang --state open
gh issue view <number> --repo jordanhubbard/nanolang --comments
gh issue edit <number> --repo jordanhubbard/nanolang --add-assignee @me
gh issue create --repo jordanhubbard/nanolang --title "<title>" --body-file /tmp/issue.md
gh issue comment <number> --repo jordanhubbard/nanolang --body-file /tmp/update.md
gh issue close <number> --repo jordanhubbard/nanolang --reason completedI search before creating an issue, record branch/file ownership in an issue comment, and link commits, PRs and test evidence before closing it. Assignment is not an atomic worker lease; I coordinate overlapping work explicitly. When resuming an old MAC task, I create or reuse a GitHub issue and link the old ID. If GitHub is unavailable, I preserve my work and report the unfiled issue; I do not fall back to MAC or claim that tracking succeeded.
Session Completion
When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.
- File follow-up issues via
gh issue create --body-file <path>and add matchingdocs/ROADMAP.mdcheckboxes for defects discovered this session - Run quality gates (if code changed) — tests, linters, builds
- Update issue status with an evidence comment; close it with
gh issue close <number>only when all acceptance criteria pass - PUSH TO REMOTE — MANDATORY:
git pull --rebase git push git status # MUST show "up to date with origin" - Clean up — clear stashes, prune remote branches
- Verify — all changes committed AND pushed
- Hand off — context for the next session
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/code-quality/RULE.mdCursor rule
- .cursor/rules/file-organization/RULE.mdCursor rule
- .cursor/rules/testing-standards/RULE.mdCursor rule
- github-issue-trackingSkill
- nanovm-opcode-debuggingSkill
- reading-nanolangSkill
- release-readinessSkill
- releasing-documentationSkill
- releasing-presentationSkill
- releasingSkill
- roadmap-executionSkill
- session-completionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

