Alex_ACT_ONE
AGENTS.md0 starsChanged 9 days agoMITView on GitHub
This repository maintains and ships Alex ACT ONE. It owns the canonical plugin skills, instructions, commands, runtime helpers, user documentation, tests, verification tooling, packaging, and release evidence. Prioritize product correctness, compatibility, reproducibility, and safe delivery through the existing release gates. Apply incident lessons as reusable product safeguards; do not turn this repository into an adopter-recovery service, fleet dashboard, or governance workspace. Other repositories own their files, backlogs, and operations. Cross-project work requires explicit scope and does not become this project's…
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 31,439 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 repository66 other files it gives its agents.
- skills/bootstrap-project/resources/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/bootstrap-project/resources/CLAUDE.mdCLAUDE.md
- act-tenetsSkill
- adversarial-reviewSkill
- annotate-screenshotSkill
- anti-hallucinationSkill
- ascii-chartSkill
- assess-brainSkill
- big-ideaSkill
- bootstrap-coreSkill
- bootstrap-projectSkill
- browser-toolsSkill
- chart-big-ideaSkill
- chart-interpretationSkill
- chart-vocabularySkill
- code-reviewSkill
- communication-craftSkill
- compile-brainSkill
- convertSkill
- corpus-qa-sweepSkill
- critical-thinkingSkill
- deep-reviewSkill
- doc-hygieneSkill
- docs-shellSkill
- docx-to-mdSkill
- ethical-reasoningSkill
- evaluate-before-adoptingSkill
- figure-generatorSkill
- flint-chartSkill
- flint-interactionsSkill
- flint-themeSkill
- git-workflowSkill
- html-to-mdSkill
- humanizerSkill
- install-visual-companionsSkill
- lint-clean-markdownSkill
- markdown-mermaidSkill
- markdown-sanitization-chainSkill
- md-to-emlSkill
- md-to-htmlSkill
- md-to-txtSkill
- md-to-wordSkill
- meditationSkill
- mutation-testingSkill
- planSkill
- platform-awarenessSkill
- print-svg-style-guideSkill
- proactive-awarenessSkill
- problem-framing-auditSkill
- project-capability-authoringSkill
- project-statusSkill
- render-chartSkill
- render-verifySkill
- rich-emailSkill
- risk-analysisSkill
- security-and-hardeningSkill
- setup-dependenciesSkill
- setup-enterprise-stackSkill
- spikeSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 1 is common, 5 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈5
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 21
Read HANDOFF.md for current state, blockers, verification, and the next action.
- Distinctive: line 28
Keep this file a stable quick start.
- Distinctive: line 39
Keep requested documents, plans, reports, code, useful helpers, generated outputs, and supporting evidence inside this repository, never …
- Distinctive: line 41
Use existing project locations and respect explicitly approved destinations.
- Distinctive: line 42
Before completion, verify final files, dependencies, links, ignore state, and actual Git state.
- Common: line 45
Do not archive credentials, runtime state, or another project's files.
≈ “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
Repository Agent Guidance
Mission and scope
This repository maintains and ships Alex ACT ONE. It owns the canonical plugin skills, instructions, commands, runtime helpers, user documentation, tests, verification tooling, packaging, and release evidence.
Prioritize product correctness, compatibility, reproducibility, and safe delivery through the existing release gates. Apply incident lessons as reusable product safeguards; do not turn this repository into an adopter-recovery service, fleet dashboard, or governance workspace. Other repositories own their files, backlogs, and operations. Cross-project work requires explicit scope and does not become this project's mission. Completed recovery and synchronization records are historical evidence, not active goals or standing authorization.
<!-- alex-act-continuity:start -->Continuity
Read HANDOFF.md for current state, blockers, verification, and the next action. ROADMAP.md is the authoritative pending-work plan; CHANGELOG.md holds completed-change history. Keep one backlog, not a parallel TODO list. Verification environments and release limits belong in docs/testing.md and RELEASE-CHECKLIST.md.
Keep this file a stable quick start. Handoff is not a changelog or a duplicate backlog. Preserve history before pruning active records, and keep unresolved tasks until evidence or an explicit decision closes them. Meditation recommends skills or automation for demonstrated needs; authoring, broader adoption, and Mall submission require separate approval. It does not write episodic or native memory. Existing episodes are historical evidence, not active guidance. Cross-project work stays explicit until separately authorized.
<!-- alex-act-continuity:end -->Project artifact storage
Keep requested documents, plans, reports, code, useful helpers, generated outputs, and supporting evidence inside this repository, never solely in session storage. Use existing project locations and respect explicitly approved destinations. Before completion, verify final files, dependencies, links, ignore state, and actual Git state. Follow the shared storage and delivery contract. Do not archive credentials, runtime state, or another project's files. This rule grants no additional implementation, installation, or publication authority and is not a host-enforced filesystem boundary.
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.