dokion-hardening
Skill1 starsChanged 4 months agoMITView on GitHub
Runs and resumes a user-authored Dokion hardening playbook, records findings and evidence, validates repairs, and reports scoped readiness. Use when a repository contains .dokion/playbook.json or the user asks to run, resume, inspect, validate, or report a Dokion hardening loop.
In this repository67 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .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-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 skill into the rules it gives an agent
12 rules. About 0 are common, 4 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use the Dokion CLI as the execution boundary.
- Very specific: line 10
Never select, install, substitute, reorder, or enable a capability.
- Very specific: line 14
Read SPEC.md when the task concerns Dokion internals.
- Very specific: line 15
Run dokion doctor and dokion validate.
- Distinctive: line 16
If no active playbook exists, stop and explain that the user must create or copy one.
- Very specific: line 17
Run dokion run only after validation succeeds.
- Very specific: line 21
Read .dokion/state.json and HARDENING.md.
- Distinctive: line 23
If the run is waiting for approval, present the exact subject and scope.
- Very specific: line 24
After the user records a decision, run dokion resume.
- Very specific: line 34
Do not infer approval from conversational tone when Dokion requires an approval record.
- Distinctive: line 64
every declared verification command exits with code 0
- Distinctive: line 80
Do not replace Bun with npm, yarn, or pnpm in this repository.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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 Hardening
Use the Dokion CLI as the execution boundary. .dokion/playbook.json is the only execution authority.
Never select, install, substitute, reorder, or enable a capability. Never upgrade a capability or edit .dokion/playbook.json. Recommendations are inert until the user changes the playbook.
Start
- Read
SPEC.mdwhen the task concerns Dokion internals. - Run
dokion doctoranddokion validate. - If no active playbook exists, stop and explain that the user must create or copy one.
- Run
dokion runonly after validation succeeds.
Resume
- Read
.dokion/state.jsonandHARDENING.md. - Run
dokion statusanddokion findings. - If the run is waiting for approval, present the exact subject and scope.
- After the user records a decision, run
dokion resume.
Approval commands
dokion approve finding:<id> --by <identity> --notes "<reason>"
dokion reject finding:<id> --by <identity> --notes "<reason>"
dokion approve step:<id> --by <identity> --notes "<reason>"Do not infer approval from conversational tone when Dokion requires an approval record.
Loop Engineering commands
dokion loop audit
dokion loop init --pattern <daily-triage|test-driven-loop|bug-fix-loop>
dokion loop cost
dokion loop sync
dokion loop contextMemory Engineering commands
dokion memory audit
dokion memory init --pattern <session-scratchpad|project-episodic-log|durable-facts-store|retrieval-budget|memory-hygiene-loop>
dokion memory status
dokion memory patternsVerification
A repair is accepted only when:
- the declared remediation command exits successfully
- the repair delta stays within the declared write scope
- suppression and test-deletion checks pass
- a required regression test was added or modified
- every declared verification command exits with code 0
A failed or rejected repair must be restored to its pre-remediation snapshot. Treat REPAIR_REJECTED, FAILED, BLOCKED, and TAINTED as non-ready states.
Development commands
Dokion itself uses Bun and TypeScript.
bun install --frozen-lockfile
bun test
bun run typecheck
bun run validate:contracts
bun run buildDo not replace Bun with npm, yarn, or pnpm in this repository.
Completion language
Report only what the configured playbook proved for the recorded commit. Include active degradations, skipped lanes, manual checks, and uncovered areas. Never state that a repository is generally production ready from a partial Dokion run.
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.

