ctrlshft
AGENTS.md0 starsChanged 6 months agoMITView on GitHub
ctrlshft is the primary, authoritative product source for Sandcastle, shft, hooks, skills, docs, and reusable automation. Public work starts HERE so review and history are native to the public project. Read ~/dotfiles/WORKSPACE_INVARIANTS.md for the full ownership test, private-only list, and guard index. Run ctrl prime "<scope>" before cross-root or file-writing tasks. Resolve these here, then pull back to dotfiles (Direction A in ~/dotfiles/seams/public-pullback.md). - Private/dotfiles overlay paths: secrets/, working/, .env* - skills/_local/**, instructions/_local/* - sandcastle.config.json + installed .github/workflows/agent-.yml — host-managed…
- Reads credentials
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 9
Read ~/dotfiles/WORKSPACE_INVARIANTS.md for the full ownership test, private-only list, and guard index.
≈ “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.
Files
AGENTS.md — ctrlshft (public)
ctrlshft is the primary, authoritative product source for Sandcastle, shft,
hooks, skills, docs, and reusable automation. Public work starts HERE so review
and history are native to the public project.
Canonical invariants
Read ~/dotfiles/WORKSPACE_INVARIANTS.md for the full ownership test, private-only
list, and guard index. Run ctrl prime "<scope>" before cross-root or
file-writing tasks.
What this repo owns (branch 1 of the ownership test)
shft/templates/workflows/**— product workflow templates (mirror of hub)shft/templates/actions/**,shft/templates/prompts/**,shft/templates/extractions/**shft/engine/**— engine source (publishes toctrlshft-hub)test/**,docs/adr/**,plans/**,bin/**REPO_TOPOLOGY.md— canonical topology doc
Resolve these here, then pull back to dotfiles (Direction A in
~/dotfiles/seams/public-pullback.md).
What it does NOT own (never)
- Private/
dotfilesoverlay paths:secrets/,working/,.env* skills/_local/**,instructions/_local/**sandcastle.config.json+ installed.github/workflows/agent-*.yml— host-managed consumer assets, never promoted FROM privatellm-gateway— runtime, unrelated to product CI
Push policy
- Work on
dev, PR tomain. Never pushdev→maindirectly. - Public pushes require
CTRL_ALLOW_PUBLIC_PUSH=1AND passingbin/validate-public-promotion.sh+bin/preflight-public-promotion.sh --range. - The
mainbranch accepts onlydev-headed promotion PRs (validate-main-pr-source).
Hub relationship
Engine + canonical templates live in arndvs/ctrlshft-hub. Changes to engine
or templates go hub-first (edit hub, run test/hub-smoke-coverage.sh, mirror
back via bin/sync-hub-templates.sh). See ~/dotfiles/seams/vendor-sandcastle.md.
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 repository40 other files it gives its agents.
- agent-assetsSkill
- agent-navigabilitySkill
- agent-session-frictionSkill
- agent-testabilitySkill
- architectSkill
- atomic-commitsSkill
- cavemanSkill
- codebase-auditSkill
- code-reviewSkill
- compliance-auditSkill
- data-object-conventionsSkill
- documentSkill
- do-workSkill
- error-auditSkill
- exploreSkill
- frontend-component-styleSkill
- grill-meSkill
- grill-with-docsSkill
- halbert-copy-editorSkill
- improve-architectureSkill
- logging-auditSkill
- mobile-devSkill
- npm-security-auditSkill
- performance-auditSkill
- plan-archiveSkill
- prd-to-issuesSkill
- press1-checkSkill
- pr-preflightSkill
- repo-hygieneSkill
- researchSkill
- review-pr-copilotSkill
- sanity-best-practicesSkill
- session-closeSkill
- sketch-the-solutionSkill
- skill-scaffolderSkill
- stress-testSkill
- systematic-debuggingSkill
- tddSkill
- visual-feedbackSkill
- write-a-prdSkill
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.

