dokion
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
Read skills/dokion-hardening/SKILL.md when the task involves Dokion execution, findings, remediation, verification, or reporting. .dokion/playbook.json is the only execution authority. Do not edit it unless the user explicitly asks to author or change the playbook. Never select, install, substitute, reorder, upgrade, or enable capabilities on the user's behalf. Run the complete set before claiming a Dokion code change is ready: For frontend changes also run: Use tests first for runtime behavior changes. Preserve immutable playbook checks, append-only evidence, exact repair rollback,…
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 repository67 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- frontend/AGENTS.mdAGENTS.md
- autoresearchSkill
- brainstormingSkill
- brandkitSkill
- create-github-action-workflow-specificationSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- dispatching-parallel-agentsSkill
- dokion-hardeningSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- full-output-enforcementSkill
- git-commitSkill
- github-publishing-workflowSkill
- google-ai-studio-web-editorSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- minimalist-uiSkill
- receiving-code-reviewSkill
- redesign-existing-projectsSkill
- requesting-code-reviewSkill
- stitch-design-tasteSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- ui-ux-design-engineSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
- autoresearchSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- dokion-hardeningSkill
- agent-playbookSkill
- archifySkill
- autoresearchSkill
- brainstormingSkill
- dispatching-parallel-agentsSkill
- dokion-automationSkill
- dokion-fullstackSkill
- dokion-hardeningSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- github-publishing-workflowSkill
- google-ai-studio-web-editorSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 1 is common, 1 is distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read skills/dokion-hardening/SKILL.md when the task involves Dokion execution, findings, remediation, verification, or reporting.
- Very specific: line 17
Run the complete set before claiming a Dokion code change is ready:
- Distinctive: line 37
Use tests first for runtime behavior changes.
- Common: line 45
Do not store credentials or private MCP configuration in the repository
≈ “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
Dokion Repository Instructions
Read skills/dokion-hardening/SKILL.md when the task involves Dokion execution, findings, remediation, verification, or reporting.
.dokion/playbook.json is the only execution authority. Do not edit it unless the user explicitly asks to author or change the playbook. Never select, install, substitute, reorder, upgrade, or enable capabilities on the user's behalf.
Stack
- Runtime: Bun
- Language: TypeScript
- Contracts: JSON Schema
- State:
.dokion/state.json - Human report:
HARDENING.md
Required verification
Run the complete set before claiming a Dokion code change is ready:
bun run test
bun run typecheck
bun run validate:contracts
bun run buildFor frontend changes also run:
cd frontend
bun install --frozen-lockfile
bun run test
bun run lint
bun run build
cd ..Use tests first for runtime behavior changes. Preserve immutable playbook checks, append-only evidence, exact repair rollback, and explicit approval records.
Repository boundaries
- Runtime-owned paths:
.dokion/**andHARDENING.md - User-owned execution configuration:
.dokion/playbook.json - Catalog entries in
dokion.jsonare inert - Recommendations may be written only as inert suggestions
- Do not store credentials or private MCP configuration in the repository
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.

