control
Skill66 starsChanged 7 months agoApache-2.0View on GitHub
View and change bkit automation settings. Shows current automation level, feature flags, trust score, and guardrail configuration.
- Reads credentials
- Deletes or force-pushes
- Commits and pushes
8 other projects use a version of this.
Adopted by
Most recently taken up by
- koltyakov/controltheir own version, first seen Nov 3, 2026
- SynchronetBBS/sbbstheir own version, first seen Oct 9, 2026
- popup-studio-ai/bkit-claude-codetheir own version, first seen Oct 8, 2026
- BackToCimaCoppi/Praxistheir own version, first seen Sep 23, 2026
- ww-w-ai/bkit-claude-codetheir own version, first seen Aug 14, 2026
- Nexus-Organization-Infosec/ClaudeSkillstheir own version, first seen Aug 4, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- popup-studio-ai/bkit-claude-code★ 605same name
- ww-w-ai/bkit-claude-code★ 605same name
- SynchronetBBS/sbbs★ 115same name
- BackToCimaCoppi/Praxis★ 6same name
- koltyakov/control★ 3same name
- Nexus-Organization-Infosec/ClaudeSkills★ 1same name
- dacrypt/tesla-claude-plugin★ 0same name
- wildewouter/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- auditSkill
- batchSkill
- bkend-authSkill
- bkend-cookbookSkill
- bkend-dataSkill
- bkend-guidesSkill
- bkend-mcpSkill
- bkend-quickstartSkill
- bkend-securitySkill
- bkend-storageSkill
- bkit-rulesSkill
- bkit-templatesSkill
- btwSkill
- code-reviewSkill
- deploySkill
- desktop-appSkill
- development-pipelineSkill
- dynamicSkill
- enterpriseSkill
- gemini-cli-learningSkill
- loopSkill
- mobile-appSkill
- output-style-setupSkill
- pdcaSkill
- phase-1-schemaSkill
- phase-2-conventionSkill
- phase-3-mockupSkill
- phase-4-apiSkill
- phase-5-design-systemSkill
- phase-6-ui-integrationSkill
- phase-7-seo-securitySkill
- phase-8-reviewSkill
- phase-9-deploymentSkill
- plan-plusSkill
- pm-discoverySkill
- qa-phaseSkill
- rollbackSkill
- simplifySkill
- skill-createSkill
- skill-statusSkill
- starterSkill
- zero-script-qaSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 90
Read .bkit/config.json for current settings
- Very specific: line 102
Update the automationLevel field
- Very specific: line 103
Write back to .bkit/config.json using write_file
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Control Skill
View and manage bkit automation levels and guardrail settings
Commands
| Command | Description | Example |
/control status | Show current automation state | /control status |
/control level L0 | Set automation to manual | /control level L0 |
/control level L1 | Set automation to semi-auto | /control level L1 |
/control level L2 | Set automation to auto-confirm | /control level L2 |
/control level L3 | Set automation to full-auto (read-only) | /control level L3 |
/control level L4 | Set automation to autonomous | /control level L4 |
/control stop | Emergency stop (immediate L0 + halt) | /control stop |
/control rollback | Rollback last N decisions | /control rollback 5 |
Automation Levels (v2.0.7+ L3/L4 unlocked via bkit hook automation channel)
| Level | Name | Behavior |
| L0 | Manual | Agent asks before every action. No automatic file writes. Emergency-stop default. |
| L1 | Semi-Auto | Agent executes known-safe operations. Asks for destructive actions. |
| L2 | Auto-Confirm | Agent executes all operations. Confirms only for irreversible actions. Default for new bkit projects. |
| L3 | Full-Auto | Read-only tools (Read/Glob/Grep/list_directory/web_fetch) auto-allowed via bkit before-tool hook. Destructive ops always asked. Requires trustScore >= 60. |
| L4 | Autonomous | All non-destructive tools auto-allowed. PDCA phase transitions automatic (via before-phase hook). Destructive ops always hard-denied (D6, 16 patterns matrix). Requires trustScore >= 80 + no recent rejections + no active 24h cooldown. |
Hard Deny (영구 차단, L4 무관)
다음 16 destructive 패턴은 어떤 level에서도 항상 차단됩니다 (cmd-parser AST 분석):
rm -rf, git push --force, drop table, truncate, delete from (no WHERE),
sudo, chmod 777, /etc/* write, ~/.ssh/* write, gpg --delete-key,
.env write, id_rsa* / *.pem / *.p12 write/delete, npm publish --force,
git config --unset credential.*, rm .git, drop database.
Auto-Downgrade (안전망)
- 5 consecutive rejections → L4/L3 → L2 + 24h cooldown
- Hard deny detected (destructive op) → L4 → L3 (no cooldown)
- Emergency stop (Ctrl+C 2회 또는
/control stop) → 즉시 L0
Gemini CLI 호환성 (v2.0.7 Wave 0 RCA로 입증)
- Non-interactive
gemini -p모드:'allow'decision suppress 정상 작동 ✓ - Interactive mode: CC issue #52822와 유사 가능성, Track B PR 검증 중
- 모든 결정은
.bkit/state/audit/{date}/decisions.jsonl에 영구 기록 (90d retention)
How to Execute
Show Status
- Read
.bkit/config.jsonfor current settings - Display:
- Current automation level (L0-L2)
- Active feature flags
- Trust score (if tracked)
- Hook configuration summary
- Guardrail rules in effect
Change Level
- Read
.bkit/config.json - Validate the requested level (L0, L1, or L2 only)
- Update the
automationLevelfield - Write back to
.bkit/config.jsonusingwrite_file - Confirm the change and explain what it means
Configuration File
Settings are stored in .bkit/config.json:
{
"automationLevel": "L1",
"features": {
"auditLog": true,
"checkpointOnDeploy": true,
"autoIterate": false,
"maxIterations": 5
},
"guardrails": {
"denyPatterns": [".env", "credentials", "secret"],
"maxFileSize": 10000,
"requireCheckpoint": true
}
}Feature Flags
| Flag | Default | Description |
auditLog | true | Enable audit trail logging |
checkpointOnDeploy | true | Auto-create checkpoint before deploy |
autoIterate | false | Auto-run iterate when match rate < 90% |
maxIterations | 5 | Maximum PDCA iteration cycles |
Guardrail Rules
Guardrails are enforced by Extension hooks (before-model, before-agent):
- File deny patterns: Block writes to sensitive files
- Max file size: Prevent accidentally large file writes
- Checkpoint requirement: Require checkpoint before destructive operations
- Review requirement: Require human review for production changes
Output Format
## bkit Control Status
| Setting | Value |
|---------|-------|
| Automation Level | L1 (Semi-Auto) |
| Audit Logging | Enabled |
| Checkpoint on Deploy | Enabled |
| Auto-Iterate | Disabled |
| Max Iterations | 5 |
### Active Guardrails
- File deny patterns: .env, credentials, secret
- Max file size: 10,000 lines
- Checkpoint required: YesDoes 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.

