heimdall-agent 0.0.0-stage → 1.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +429 -2
- package/README.pt-BR.md +429 -0
- package/agents/cloud-engineer.md +77 -0
- package/agents/code-sentinel.md +77 -0
- package/agents/database-architect.md +38 -0
- package/agents/frontend-designer.md +44 -0
- package/agents/mobile-designer.md +33 -0
- package/agents/modernizer.md +66 -0
- package/agents/orchestrator.md +94 -0
- package/agents/reviewer.md +111 -0
- package/agents/security-auditor.md +38 -0
- package/agents/tester.md +107 -0
- package/commands/grill-me.md +26 -0
- package/commands/orchestrate.md +37 -0
- package/commands/orchestrator.md +37 -0
- package/commands/plan.md +30 -0
- package/config/agents.json +183 -0
- package/config/mcp.json +72 -0
- package/config/models.json +115 -0
- package/config/profiles.json +86 -0
- package/config/skills.json +683 -0
- package/docs/SKILLS.md +378 -0
- package/docs/designs/old/2026-10-31 plan-lifecycle-backlog-and-clean-code-skill.md +87 -0
- package/docs/designs/old/2026-11-02 skill-upstream-audit-and-update.md +105 -0
- package/docs/designs/old/2026-11-05 communication-doctrine-bluf-ste.md +94 -0
- package/docs/designs/old/2026-11-06-cloud-engineer-and-resilience-synthesis.md +67 -0
- package/docs/designs/old/2026-11-06-herdr-native-agent-orchestration.md +45 -0
- package/docs/runs/skill-audit/add_progressive_disclosure.cjs +30 -0
- package/docs/runs/skill-audit/check_heimdall_skills.ps1 +9 -0
- package/docs/runs/skill-audit/compare_classics.ps1 +26 -0
- package/docs/runs/skill-audit/compare_taste.ps1 +12 -0
- package/docs/runs/skill-audit/customization-report.json +380 -0
- package/docs/runs/skill-audit/diff_pending_skills.cjs +94 -0
- package/docs/runs/skill-audit/fetch_and_apply_skill.cjs +58 -0
- package/docs/runs/skill-audit/fetch_and_apply_taste_v2.cjs +65 -0
- package/docs/runs/skill-audit/inspect_pending_skills.cjs +71 -0
- package/docs/runs/skill-audit/inventory.json +308 -0
- package/docs/runs/skill-audit/list_local_taste.ps1 +1 -0
- package/docs/runs/skill-audit/phase5-update-plan.json +595 -0
- package/docs/runs/skill-audit/phase5-update-plan.md +138 -0
- package/docs/runs/skill-audit/probe.ps1 +16 -0
- package/docs/runs/skill-audit/probe_classics_branches.ps1 +3 -0
- package/docs/runs/skill-audit/probe_commits.ps1 +15 -0
- package/docs/runs/skill-audit/probe_repos.ps1 +17 -0
- package/docs/runs/skill-audit/probe_sentry_sec.ps1 +3 -0
- package/docs/runs/skill-audit/probe_sentry_sweep.ps1 +5 -0
- package/docs/runs/skill-audit/probe_snyk.ps1 +3 -0
- package/docs/runs/skill-audit/probe_snyk_recipes.ps1 +5 -0
- package/docs/runs/skill-audit/probe_taste_branches.ps1 +8 -0
- package/docs/runs/skill-audit/probe_taste_v19.ps1 +3 -0
- package/docs/runs/skill-audit/probe_user_repos.ps1 +19 -0
- package/docs/runs/skill-audit/prune_taste_skills.cjs +22 -0
- package/docs/runs/skill-audit/run_phase1_2.cjs +142 -0
- package/docs/runs/skill-audit/run_phase6_verification.cjs +107 -0
- package/docs/runs/skill-audit/show_16_details.ps1 +25 -0
- package/docs/runs/skill-audit/show_20_skills.ps1 +28 -0
- package/docs/runs/skill-audit/show_classics_diff.cjs +37 -0
- package/docs/runs/skill-audit/sync_agent_markdowns.cjs +30 -0
- package/docs/runs/skill-audit/taste-skill-upstream.md +542 -0
- package/docs/runs/skill-audit/update-manifest.md +88 -0
- package/docs/runs/skill-audit/update_config_skills.cjs +52 -0
- package/docs/runs/skill-audit/update_registry_phase7.cjs +83 -0
- package/docs/runs/skill-audit/upstream-status.json +563 -0
- package/docs/runs/skill-audit/verification-results.json +252 -0
- package/doctrine/AGENTS.md +54 -0
- package/hooks/git/pre-commit +11 -0
- package/hooks/git/pre-push +26 -0
- package/hooks/heimdall-hook.cjs +231 -0
- package/hooks/herdr-agent-state.ps1 +55 -0
- package/hooks/hooks.json +36 -0
- package/lib/catalog-sync.cjs +162 -0
- package/lib/hermes-context.cjs +57 -0
- package/lib/model-context.cjs +123 -0
- package/lib/path-discovery.cjs +94 -0
- package/package.json +58 -4
- package/playbooks/01-interactive-grilling-gate.md +54 -0
- package/playbooks/02-fast-code-deep-verification.md +32 -0
- package/playbooks/03-adversarial-code-review.md +56 -0
- package/playbooks/04-design-system-and-taste.md +27 -0
- package/playbooks/05-canonical-plan-template.md +104 -0
- package/playbooks/06-model-registry-matrix.md +83 -0
- package/playbooks/07-legacy-code-modernization.md +74 -0
- package/playbooks/08-backlog-and-change-request-flow.md +122 -0
- package/setup.mjs +2184 -0
- package/skills/antislop/SKILL.md +700 -0
- package/skills/antislop/VERSION +1 -0
- package/skills/antislop-code/SKILL.md +128 -0
- package/skills/antislop-copywriting/SKILL.md +372 -0
- package/skills/antislop-human/LICENSE-web-quality-skills +21 -0
- package/skills/antislop-human/SKILL.md +204 -0
- package/skills/antislop-human/contrast-check.py +168 -0
- package/skills/antislop-human/contrast-mcp.py +121 -0
- package/skills/antislop-human/references/A11Y-PATTERNS.md +249 -0
- package/skills/antislop-human/references/WCAG.md +127 -0
- package/skills/antislop-layoutmobile/SKILL.md +170 -0
- package/skills/antislop-ui/LICENSE-web-quality-skills +21 -0
- package/skills/antislop-ui/SKILL.md +344 -0
- package/skills/antislop-ui/references/CORE-WEB-VITALS.md +181 -0
- package/skills/antislop-ui/references/WEB-BASELINE.md +28 -0
- package/skills/brainstorming/SKILL.md +294 -0
- package/skills/brainstorming/builder-check-prompt.md +23 -0
- package/skills/brainstorming/scripts/frame-template.html +213 -0
- package/skills/brainstorming/scripts/helper.js +167 -0
- package/skills/brainstorming/scripts/server.cjs +723 -0
- package/skills/brainstorming/scripts/start-server.sh +209 -0
- package/skills/brainstorming/scripts/stop-server.sh +120 -0
- package/skills/brainstorming/spec-document-reviewer-prompt.md +49 -0
- package/skills/brainstorming/visual-companion.md +299 -0
- package/skills/brandkit/SKILL.md +798 -0
- package/skills/brutalist-skill/SKILL.md +93 -0
- package/skills/caveman/README.md +68 -0
- package/skills/caveman/SKILL.md +89 -0
- package/skills/claude-collaborator/SKILL.md +53 -0
- package/skills/clean-code/SKILL.md +152 -0
- package/skills/cloudflare-security-audit/AI-AND-LLM.md +83 -0
- package/skills/cloudflare-security-audit/ATTACK-CLASSES.md +130 -0
- package/skills/cloudflare-security-audit/CLIENT-SIDE.md +83 -0
- package/skills/cloudflare-security-audit/CLOUD-AND-DEPLOYMENT.md +86 -0
- package/skills/cloudflare-security-audit/DATA-ISOLATION-AND-LIFECYCLE.md +84 -0
- package/skills/cloudflare-security-audit/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -0
- package/skills/cloudflare-security-audit/HUNTING.md +251 -0
- package/skills/cloudflare-security-audit/LICENSE +21 -0
- package/skills/cloudflare-security-audit/MEMORY-SAFETY-AND-BINARY.md +101 -0
- package/skills/cloudflare-security-audit/PROTOCOLS-RPC-AND-MESSAGING.md +81 -0
- package/skills/cloudflare-security-audit/README.md +106 -0
- package/skills/cloudflare-security-audit/RECONNAISSANCE.md +156 -0
- package/skills/cloudflare-security-audit/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -0
- package/skills/cloudflare-security-audit/SKILL.md +192 -0
- package/skills/cloudflare-security-audit/SUPPLY-CHAIN-AND-RELEASE.md +73 -0
- package/skills/cloudflare-security-audit/VALIDATION-AND-REPORTING.md +186 -0
- package/skills/cloudflare-security-audit/WEB-PROTOCOL-AND-AUTH.md +105 -0
- package/skills/cloudflare-security-audit/report-schema.json +461 -0
- package/skills/cloudflare-security-audit/validate-coverage-ledger.cjs +872 -0
- package/skills/cloudflare-security-audit/validate-coverage-ledger.test.cjs +740 -0
- package/skills/cloudflare-security-audit/validate-findings.cjs +773 -0
- package/skills/cloudflare-security-audit/validate-findings.test.cjs +652 -0
- package/skills/codex-collaborator/SKILL.md +65 -0
- package/skills/communication-doctrine/SKILL.md +89 -0
- package/skills/diagnosing-superpowers/SKILL.md +120 -0
- package/skills/diagnosing-superpowers/prompts/analyst-common.md +38 -0
- package/skills/diagnosing-superpowers/prompts/cost-and-time.md +28 -0
- package/skills/diagnosing-superpowers/prompts/plan-adherence.md +29 -0
- package/skills/diagnosing-superpowers/prompts/quality-evidence.md +26 -0
- package/skills/diagnosing-superpowers/prompts/repeated-work.md +30 -0
- package/skills/diagnosing-superpowers/prompts/request-conflicts.md +20 -0
- package/skills/diagnosing-superpowers/prompts/scrub-audit.md +33 -0
- package/skills/diagnosing-superpowers/prompts/scrub.md +29 -0
- package/skills/diagnosing-superpowers/prompts/similar-session.md +38 -0
- package/skills/diagnosing-superpowers/prompts/skill-timeline.md +30 -0
- package/skills/diagnosing-superpowers/prompts/stumbles.md +28 -0
- package/skills/diagnosing-superpowers/references/context-safety.md +22 -0
- package/skills/diagnosing-superpowers/references/github-issues.md +47 -0
- package/skills/diagnosing-superpowers/references/redaction-policy.md +34 -0
- package/skills/diagnosing-superpowers/references/session-discovery.md +31 -0
- package/skills/diagnosing-superpowers/templates/bundle-README.md +77 -0
- package/skills/diagnosing-superpowers/templates/case.md +64 -0
- package/skills/diagnosing-superpowers/templates/issue.md +70 -0
- package/skills/diagnosing-superpowers/templates/report.md +82 -0
- package/skills/dispatching-parallel-agents/SKILL.md +167 -0
- package/skills/executing-plans/SKILL.md +321 -0
- package/skills/executing-plans/scripts/task-done +52 -0
- package/skills/executing-plans/scripts/task-start +28 -0
- package/skills/finishing-a-development-branch/SKILL.md +225 -0
- package/skills/gemini-collaborator/SKILL.md +53 -0
- package/skills/herdr/SKILL.md +243 -0
- package/skills/image-to-code-skill/SKILL.md +1228 -0
- package/skills/imagegen-frontend-mobile/SKILL.md +1465 -0
- package/skills/imagegen-frontend-web/SKILL.md +987 -0
- package/skills/karpathy-guidelines/SKILL.md +67 -0
- package/skills/mcp-engineering/SKILL.md +74 -0
- package/skills/minimalist-skill/SKILL.md +87 -0
- package/skills/output-skill/SKILL.md +49 -0
- package/skills/owasp-security/SKILL.md +206 -0
- package/skills/owasp-security/reference/config-and-supply-chain.md +344 -0
- package/skills/owasp-security/reference/languages.md +372 -0
- package/skills/owasp-security/reference/owasp-report.md +1140 -0
- package/skills/owasp-security/reference/review-checklist.md +132 -0
- package/skills/ponytail/SKILL.md +52 -0
- package/skills/postgres-best-practices/SKILL.md +42 -0
- package/skills/postgres-best-practices/references/_contributing.md +170 -0
- package/skills/postgres-best-practices/references/_sections.md +39 -0
- package/skills/postgres-best-practices/references/_template.md +34 -0
- package/skills/postgres-best-practices/references/advanced-full-text-search.md +55 -0
- package/skills/postgres-best-practices/references/advanced-jsonb-indexing.md +49 -0
- package/skills/postgres-best-practices/references/backup-restore.md +372 -0
- package/skills/postgres-best-practices/references/bulk-loading.md +315 -0
- package/skills/postgres-best-practices/references/conn-idle-timeout.md +46 -0
- package/skills/postgres-best-practices/references/conn-limits.md +44 -0
- package/skills/postgres-best-practices/references/conn-pooling.md +41 -0
- package/skills/postgres-best-practices/references/conn-prepared-statements.md +46 -0
- package/skills/postgres-best-practices/references/connection-pooling.md +310 -0
- package/skills/postgres-best-practices/references/data-batch-inserts.md +54 -0
- package/skills/postgres-best-practices/references/data-n-plus-one.md +53 -0
- package/skills/postgres-best-practices/references/data-pagination.md +50 -0
- package/skills/postgres-best-practices/references/data-upsert.md +50 -0
- package/skills/postgres-best-practices/references/hot-standby.md +221 -0
- package/skills/postgres-best-practices/references/indexing.md +318 -0
- package/skills/postgres-best-practices/references/lock-advisory.md +56 -0
- package/skills/postgres-best-practices/references/lock-deadlock-prevention.md +68 -0
- package/skills/postgres-best-practices/references/lock-short-transactions.md +50 -0
- package/skills/postgres-best-practices/references/lock-skip-locked.md +54 -0
- package/skills/postgres-best-practices/references/logical-replication.md +610 -0
- package/skills/postgres-best-practices/references/major-version-upgrades.md +334 -0
- package/skills/postgres-best-practices/references/monitor-explain-analyze.md +45 -0
- package/skills/postgres-best-practices/references/monitor-pg-stat-statements.md +55 -0
- package/skills/postgres-best-practices/references/monitor-vacuum-analyze.md +55 -0
- package/skills/postgres-best-practices/references/performance-diagnostics.md +553 -0
- package/skills/postgres-best-practices/references/query-composite-indexes.md +44 -0
- package/skills/postgres-best-practices/references/query-covering-indexes.md +40 -0
- package/skills/postgres-best-practices/references/query-index-types.md +48 -0
- package/skills/postgres-best-practices/references/query-missing-indexes.md +43 -0
- package/skills/postgres-best-practices/references/query-optimization.md +294 -0
- package/skills/postgres-best-practices/references/query-partial-indexes.md +45 -0
- package/skills/postgres-best-practices/references/query-patterns.md +566 -0
- package/skills/postgres-best-practices/references/schema-constraints.md +80 -0
- package/skills/postgres-best-practices/references/schema-data-types.md +46 -0
- package/skills/postgres-best-practices/references/schema-design.md +362 -0
- package/skills/postgres-best-practices/references/schema-foreign-key-indexes.md +59 -0
- package/skills/postgres-best-practices/references/schema-lowercase-identifiers.md +55 -0
- package/skills/postgres-best-practices/references/schema-partitioning.md +55 -0
- package/skills/postgres-best-practices/references/schema-primary-keys.md +61 -0
- package/skills/postgres-best-practices/references/security-privileges.md +54 -0
- package/skills/postgres-best-practices/references/security-rls-basics.md +50 -0
- package/skills/postgres-best-practices/references/security-rls-performance.md +63 -0
- package/skills/postgres-best-practices/references/security-roles.md +489 -0
- package/skills/postgres-best-practices/references/transaction-isolation.md +344 -0
- package/skills/progressive-disclosure/SKILL.md +68 -0
- package/skills/project-hygiene/SKILL.md +48 -0
- package/skills/pstack-discipline/SKILL.md +40 -0
- package/skills/receiving-code-review/SKILL.md +205 -0
- package/skills/redesign-skill/SKILL.md +178 -0
- package/skills/requesting-code-review/SKILL.md +95 -0
- package/skills/requesting-code-review/code-reviewer.md +198 -0
- package/skills/security-audit-sweep/SKILL.md +44 -0
- package/skills/snyk-agent-scan/SKILL.md +25 -0
- package/skills/soft-skill/SKILL.md +99 -0
- package/skills/stitch-skill/DESIGN.md +121 -0
- package/skills/stitch-skill/SKILL.md +185 -0
- package/skills/strix-security/SKILL.md +66 -0
- package/skills/subagent-driven-development/SKILL.md +336 -0
- package/skills/subagent-driven-development/adversarial-reviewer-prompt.md +18 -0
- package/skills/subagent-driven-development/designer-prompt.md +15 -0
- package/skills/subagent-driven-development/hygiene-checker-prompt.md +15 -0
- package/skills/subagent-driven-development/implementer-prompt.md +154 -0
- package/skills/subagent-driven-development/re-review-prompt.md +115 -0
- package/skills/subagent-driven-development/references/batching.md +11 -0
- package/skills/subagent-driven-development/references/cannot-verify.md +10 -0
- package/skills/subagent-driven-development/references/final-review.md +47 -0
- package/skills/subagent-driven-development/references/fix-loop.md +77 -0
- package/skills/subagent-driven-development/references/handling-reports.md +15 -0
- package/skills/subagent-driven-development/references/preflight.md +26 -0
- package/skills/subagent-driven-development/references/resuming.md +12 -0
- package/skills/subagent-driven-development/scripts/review-package +53 -0
- package/skills/subagent-driven-development/scripts/sdd-workspace +87 -0
- package/skills/subagent-driven-development/scripts/task-brief +43 -0
- package/skills/subagent-driven-development/security-auditor-prompt.md +15 -0
- package/skills/subagent-driven-development/task-reviewer-prompt.md +207 -0
- package/skills/subagent-driven-development/tester-prompt.md +17 -0
- package/skills/systematic-debugging/CREATION-LOG.md +119 -0
- package/skills/systematic-debugging/SKILL.md +283 -0
- package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -0
- package/skills/systematic-debugging/condition-based-waiting.md +115 -0
- package/skills/systematic-debugging/defense-in-depth.md +122 -0
- package/skills/systematic-debugging/find-polluter.sh +72 -0
- package/skills/systematic-debugging/root-cause-tracing.md +169 -0
- package/skills/systematic-debugging/test-academic.md +14 -0
- package/skills/systematic-debugging/test-pressure-1.md +58 -0
- package/skills/systematic-debugging/test-pressure-2.md +68 -0
- package/skills/systematic-debugging/test-pressure-3.md +69 -0
- package/skills/taste-skill/SKILL.md +542 -0
- package/skills/taste-skill/references/app-screens.md +1199 -0
- package/skills/taste-skill/references/colour.md +141 -0
- package/skills/taste-skill/references/copy.md +177 -0
- package/skills/taste-skill/references/critique.md +182 -0
- package/skills/taste-skill/references/imagery.md +791 -0
- package/skills/taste-skill/references/layout.md +292 -0
- package/skills/taste-skill/references/motion.md +980 -0
- package/skills/taste-skill/references/research.md +356 -0
- package/skills/taste-skill/references/scenes.md +174 -0
- package/skills/taste-skill/references/tells.md +115 -0
- package/skills/taste-skill/references/type.md +170 -0
- package/skills/test-driven-development/SKILL.md +330 -0
- package/skills/test-driven-development/writing-good-tests.md +198 -0
- package/skills/thermo/SKILL.md +67 -0
- package/skills/threat-modeling/SKILL.md +55 -0
- package/skills/trailofbits-audit-context/SKILL.md +72 -0
- package/skills/trailofbits-audit-context/agents/openai.yaml +6 -0
- package/skills/trailofbits-audit-context/assets/trail-of-bits-mark.svg +1 -0
- package/skills/trailofbits-audit-context/resources/ANALYSIS_FORMAT.md +68 -0
- package/skills/trailofbits-audit-context/resources/DOMAIN_NOTES.md +73 -0
- package/skills/trailofbits-audit-context/resources/FUNCTION_MICRO_ANALYSIS_EXAMPLE.md +174 -0
- package/skills/trailofbits-insecure-defaults/README.md +104 -0
- package/skills/trailofbits-insecure-defaults/SKILL.md +21 -0
- package/skills/trailofbits-insecure-defaults/commands/audit.md +35 -0
- package/skills/trailofbits-insecure-defaults/references/debug-features.json +13 -0
- package/skills/trailofbits-insecure-defaults/references/debug-features.md +75 -0
- package/skills/trailofbits-insecure-defaults/references/default-credentials.json +12 -0
- package/skills/trailofbits-insecure-defaults/references/default-credentials.md +76 -0
- package/skills/trailofbits-insecure-defaults/references/fail-open-security.json +11 -0
- package/skills/trailofbits-insecure-defaults/references/fail-open-security.md +70 -0
- package/skills/trailofbits-insecure-defaults/references/fallback-secrets.json +11 -0
- package/skills/trailofbits-insecure-defaults/references/fallback-secrets.md +70 -0
- package/skills/trailofbits-insecure-defaults/references/permissive-access.json +13 -0
- package/skills/trailofbits-insecure-defaults/references/permissive-access.md +62 -0
- package/skills/trailofbits-insecure-defaults/references/weak-crypto.json +13 -0
- package/skills/trailofbits-insecure-defaults/references/weak-crypto.md +71 -0
- package/skills/trailofbits-triage-brocards/SKILL.md +208 -0
- package/skills/trailofbits-triage-brocards/references/brocards-detail.md +220 -0
- package/skills/using-git-worktrees/SKILL.md +167 -0
- package/skills/using-superpowers/SKILL.md +65 -0
- package/skills/using-superpowers/references/antigravity-tools.md +23 -0
- package/skills/using-superpowers/references/claude-code-tools.md +29 -0
- package/skills/using-superpowers/references/codex-tools.md +108 -0
- package/skills/using-superpowers/references/gemini-tools.md +63 -0
- package/skills/using-superpowers/references/hermes-tools.md +56 -0
- package/skills/using-superpowers/references/muse-tools.md +35 -0
- package/skills/using-superpowers/references/pi-tools.md +16 -0
- package/skills/verification-before-completion/SKILL.md +120 -0
- package/skills/writing-plans/SKILL.md +207 -0
- package/skills/writing-skills/SKILL.md +399 -0
- package/skills/writing-skills/anthropic-best-practices.md +1150 -0
- package/skills/writing-skills/examples/CLAUDE_MD_TESTING.md +189 -0
- package/skills/writing-skills/graphviz-conventions.dot +172 -0
- package/skills/writing-skills/persuasion-principles.md +187 -0
- package/skills/writing-skills/references/CLAUDE_MD_TESTING.md +189 -0
- package/skills/writing-skills/references/anthropic-best-practices.md +1150 -0
- package/skills/writing-skills/references/bulletproofing.md +80 -0
- package/skills/writing-skills/references/discovery.md +201 -0
- package/skills/writing-skills/references/flowcharts.md +37 -0
- package/skills/writing-skills/references/graphviz-conventions.dot +172 -0
- package/skills/writing-skills/references/persuasion-principles.md +187 -0
- package/skills/writing-skills/references/testing-skills-with-subagents.md +384 -0
- package/skills/writing-skills/render-graphs.js +169 -0
- package/skills/writing-skills/testing-skills-with-subagents.md +384 -0
- package/tools/archive/claude-bridge.cmd +2 -0
- package/tools/archive/claude-bridge.ps1 +493 -0
- package/tools/archive/claude-bridge.sh +17 -0
- package/tools/archive/codex-bridge.cmd +2 -0
- package/tools/archive/codex-bridge.ps1 +518 -0
- package/tools/archive/codex-bridge.sh +17 -0
- package/tools/archive/codexcli-bridge.cmd +2 -0
- package/tools/archive/codexcli-bridge.ps1 +5 -0
- package/tools/archive/gemini-bridge.cmd +2 -0
- package/tools/archive/gemini-bridge.ps1 +464 -0
- package/tools/archive/gemini-bridge.sh +17 -0
package/README.md
CHANGED
|
@@ -1,3 +1,430 @@
|
|
|
1
|
-
#
|
|
1
|
+
# `heimdall-agent` — Multi-Agent Engineering Sentinel & Environment Bootstrapper
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
<p align="left">
|
|
4
|
+
<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square" alt="License: MIT" /></a>
|
|
5
|
+
<a href="https://nodejs.org"><img src="https://img.shields.io/badge/node-%3E%3D18.0.0-339933.svg?style=flat-square&logo=node.js&logoColor=white" alt="Node >= 18" /></a>
|
|
6
|
+
<a href="#10-predefined-agent-personas"><img src="https://img.shields.io/badge/agents-10%20predefined-orange.svg?style=flat-square" alt="Agents: 10 Predefined" /></a>
|
|
7
|
+
<a href="#skill-inventory-56-modules-across-24-toolkits"><img src="https://img.shields.io/badge/skills-24%20toolkits%20%2856%20modules%29-blueviolet.svg?style=flat-square" alt="Skills: 24 Toolkits (56 Modules)" /></a>
|
|
8
|
+
<a href="#supported-tools--runtimes"><img src="https://img.shields.io/badge/runtimes-Antigravity%20%7C%20Claude%20%7C%20Codex%20%7C%20Hermes%20%7C%20OpenClaw-black.svg?style=flat-square" alt="Runtimes" /></a>
|
|
9
|
+
</p>
|
|
10
|
+
|
|
11
|
+
🌐 **Language / Idioma:** **English** | [Português (Brasil)](README.pt-BR.md)
|
|
12
|
+
|
|
13
|
+
Heimdall is a portable bootstrap toolkit and quality sentinel for multi-agent software engineering. It enforces planning gates before code generation, prevents AI slop, isolates module boundaries, and synchronizes **10 specialized agent personas** and **56 modular skills** across **Google Antigravity**, **Claude Code**, **OpenAI Codex CLI**, **Hermes Agent**, **OpenClaw**, **OpenDesign**, and **Claude Desktop**.
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
<a id="table-of-contents"></a>
|
|
18
|
+
## Table of Contents
|
|
19
|
+
|
|
20
|
+
- [1. What is Heimdall?](#1-what-is-heimdall)
|
|
21
|
+
- [2. What it Does](#2-what-it-does)
|
|
22
|
+
- [3. How it Works (Architecture, Files & Hooks)](#3-how-it-works)
|
|
23
|
+
- [4. How to Install](#4-how-to-install)
|
|
24
|
+
- [5. How to Use (CLI & Slash Commands)](#5-how-to-use)
|
|
25
|
+
- [6. Full List of Skills & Agents](#6-full-list-of-skills--agents)
|
|
26
|
+
- [7. Additional Companion Tools](#7-additional-companion-tools)
|
|
27
|
+
- [License](#license)
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
31
|
+
<a id="1-what-is-heimdall"></a>
|
|
32
|
+
## 1. What is Heimdall?
|
|
33
|
+
|
|
34
|
+
**Heimdall** is an environment bootstrapper and multi-agent coordination layer for AI coding tools.
|
|
35
|
+
|
|
36
|
+
Instead of manually maintaining scattered custom instructions, system prompts, and configuration files across different AI clients, Heimdall provides a single source of truth:
|
|
37
|
+
* **Modular Skills**: 56 task-activated capabilities (such as database design, security audits, design token enforcement, progressive disclosure, and debugging) that load on demand instead of wasting prompt tokens.
|
|
38
|
+
* **Specialized Agent Personas**: 10 predefined roles with isolated context windows (`orchestrator`, `tester`, `frontend-designer`, `mobile-designer`, `reviewer`, `security-auditor`, `database-architect`, `code-sentinel`, `modernizer`, `cloud-engineer`).
|
|
39
|
+
* **Universal Doctrine**: Central rules (`AGENTS.md`) synchronized across all harnesses, enforcing planning gates, test-driven development (TDD), and minimal surgical code edits.
|
|
40
|
+
|
|
41
|
+
Heimdall runs on **Windows, macOS, and Linux**, using native filesystem junctions and symlinks to keep all AI harnesses synchronized with zero file duplication.
|
|
42
|
+
|
|
43
|
+
[↑ Back to top](#table-of-contents)
|
|
44
|
+
|
|
45
|
+
---
|
|
46
|
+
|
|
47
|
+
<a id="2-what-it-does"></a>
|
|
48
|
+
## 2. What it Does
|
|
49
|
+
|
|
50
|
+
Heimdall transforms unconstrained AI coding assistants into disciplined, multi-agent engineering teams:
|
|
51
|
+
|
|
52
|
+
1. **Enforces Interactive Planning Gates**: Halts immediate code generation on complex tasks. Interrogates requirements, asks probing questions on failure modes, and presents architectural alternatives before locking the plan.
|
|
53
|
+
2. **Eliminates AI Slop & Restrains Code**: Enforces Karpathy simplicity guidelines (50 lines over 200, surgical edits only) and purges AI conversational fluff, boilerplate comments, and decorative CSS defaults.
|
|
54
|
+
3. **Implements Test-Driven Development (TDD)**: Requires failing automated tests before writing implementation code. Prohibits pseudo-verification (`curl 200`, `grep`, container status).
|
|
55
|
+
4. **Mandates Playwright E2E Browser Testing**: Requires active Playwright browser verification for any interactive UI or user-facing changes.
|
|
56
|
+
5. **Adversarial Peer Review**: Dispatches context-blinded reviewers to inspect git diffs for edge cases, silent regressions, and unhandled failure branches.
|
|
57
|
+
6. **Intercepts Dangerous Operations**: Evaluates shell commands and file mutations via lifecycle hooks to block destructive root wiping and force-pushes to protected branches.
|
|
58
|
+
|
|
59
|
+
### Comparison: Vanilla AI Coding vs. Heimdall
|
|
60
|
+
|
|
61
|
+
| Area | Vanilla AI Coding | With Heimdall |
|
|
62
|
+
| :--- | :--- | :--- |
|
|
63
|
+
| **Initial Prompt** | AI immediately generates 300 lines of unverified code. | **Interactive Gate**: AI pauses, interrogates edge cases, and presents 2 architectural options. |
|
|
64
|
+
| **Code Review** | AI rubber-stamps its own code with conversational praise. | **Context-Blinded Review**: Stateless reviewer inspects diffs without conversational bias. |
|
|
65
|
+
| **Code Restraint** | Bloated wrappers, defensive boilerplate, speculative options. | **Karpathy Simplicity**: Minimum code, surgical edits, zero unprompted refactoring. |
|
|
66
|
+
| **Verification** | AI claims "done!" without testing or relies on shallow checks. | **TDD & Playwright**: Failing test first; active browser DOM assertions for UI. |
|
|
67
|
+
| **Safety** | AI can execute destructive commands or force push to main. | **Lifecycle Hooks**: Blocks `rm -rf /` and force pushes to `main`/`master` at runtime and Git level. |
|
|
68
|
+
| **Configuration** | Scattered, drifting prompt files across multiple tools. | **Single Source of Truth**: Linked via native junctions/symlinks in 1 second. |
|
|
69
|
+
|
|
70
|
+
[↑ Back to top](#table-of-contents)
|
|
71
|
+
|
|
72
|
+
---
|
|
73
|
+
|
|
74
|
+
<a id="3-how-it-works"></a>
|
|
75
|
+
## 3. How it Works (Architecture, Files & Hooks)
|
|
76
|
+
|
|
77
|
+
Heimdall sits between your AI coding clients and your codebase, deploying standardized files, hooks, and doctrine across your system.
|
|
78
|
+
|
|
79
|
+
### 1. Files & Directories Touched
|
|
80
|
+
|
|
81
|
+
When Heimdall bootstraps, it establishes live junctions (Windows) or symlinks (POSIX) from this repository to your target tool configuration directories:
|
|
82
|
+
|
|
83
|
+
| Source in Heimdall | Deployed Location | Purpose |
|
|
84
|
+
| :--- | :--- | :--- |
|
|
85
|
+
| `skills/` | `~/.<tool>/skills/` | 56 domain toolkits loaded progressively on demand. |
|
|
86
|
+
| `agents/` | `~/.<tool>/agents/` | 10 specialized agent persona definitions. |
|
|
87
|
+
| `hooks/` | `~/.claude/hooks/` | Event-driven lifecycle hooks for Claude Code CLI. |
|
|
88
|
+
| `hooks/git/` | `.git/hooks/` (optional) | Universal native Git pre-push hook for all tools. |
|
|
89
|
+
| `doctrine/AGENTS.md` | `~/.claude/CLAUDE.md`<br>`~/.gemini/GEMINI.md`<br>`~/.codex/AGENTS.md`<br>`~/.hermes/AGENTS.md` | Universal cross-agent doctrine and operational constraints. |
|
|
90
|
+
| `playbooks/` | `~/.<tool>/playbooks/` | Operational playbooks (grilling gate, TDD, reviews, plans, backlog & CR flow). |
|
|
91
|
+
| `commands/` | `~/.claude/commands/` | Slash commands (`/orchestrator`, `/orchestrate`, `/plan`, `/grill-me`). |
|
|
92
|
+
| `tools/` | `PATH` candidate directory | Cross-model bridge scripts (`claude-bridge`, `gemini-bridge`, `codex-bridge`) and `heimdall` CLI. |
|
|
93
|
+
| `docs/designs/` | Workspace root | Canonical plan home (`YYYY-MM-DD <name>.md`); verified plans archived to `old/`. |
|
|
94
|
+
| `docs/backlog.md` | Workspace root | Single-source-of-truth product backlog and Change Request ledger. |
|
|
95
|
+
|
|
96
|
+
### 2. The Google Elephant-Goldfish Model (EGM)
|
|
97
|
+
|
|
98
|
+
Heimdall adopts the core division of labor from [`google/elephant-goldfish-model`](https://github.com/google/elephant-goldfish-model):
|
|
99
|
+
|
|
100
|
+
* **The Elephant (Coordinator)**: The primary session and [`orchestrator`](#10-predefined-agent-personas) persona retain long-term memory, project narrative, and deep contextual history.
|
|
101
|
+
* **The Goldfish (Reviewers & Testers)**: Subagents dispatched for code review (`reviewer`) and bug diagnosis (`tester`) are intentionally blinded to conversational backstory and author debates. They evaluate raw git diffs and acceptance criteria directly, preventing confirmation bias and rubber-stamping.
|
|
102
|
+
* **The 3-Tier Boundary Ladder**:
|
|
103
|
+
- **Tier 1 (Spike / Bugfix < 50 LOC)**: Zero ceremony. Minimal surgical code with a failing test first.
|
|
104
|
+
- **Tier 2 (Bounded Feature)**: Fast in-chat design check with critic and readiness reviews.
|
|
105
|
+
- **Tier 3 (Architectural)**: Spec written to disk (`docs/designs/<feature>.md`), 4-stage review (Zoom Out, Comprehension, Critique, Readiness), and a 5-round convergence ledger.
|
|
106
|
+
* **Adaptive Multi-Model Execution**: In Herdr (`HERDR_ENV=1`), Heimdall routes reviews across different models (e.g. Gemini Elephant validated by Claude/Codex) via native Herdr multiplexing; otherwise, it falls back to stateless child subagents on the same model.
|
|
107
|
+
|
|
108
|
+
### 3. Event-Driven Lifecycle Hooks
|
|
109
|
+
|
|
110
|
+
Heimdall includes zero-dependency runtime hooks ([`hooks/heimdall-hook.cjs`](hooks/heimdall-hook.cjs)) registered in `~/.claude/settings.json`:
|
|
111
|
+
|
|
112
|
+
* **`PreToolUse` (Bash/PowerShell)**:
|
|
113
|
+
- **Blocks Destructive Commands**: Halts operations like `rm -rf /` or `rmdir /s /q C:\` (exit code 2).
|
|
114
|
+
- **Branch-Aware Force Push Protection**: Blocks `git push --force` targeting `main`, `master`, `release`, or `production` (explicitly or while checked out on those branches). Force pushes to feature branches (`feature/*`, `bugfix/*`) are permitted with an advisory.
|
|
115
|
+
- **Blocks Secret Commits**: Halts staging unencrypted `.env`, `id_rsa`, or `*.pem` files.
|
|
116
|
+
* **`PreToolUse` (Write)**:
|
|
117
|
+
- **Karpathy Restraint Warning**: Emits an advisory if an AI attempts to generate a single file exceeding 800 lines.
|
|
118
|
+
* **`PostToolUse` (Edit/Write)**:
|
|
119
|
+
- **Verification Reminder**: Emits a reminder to run automated tests or browser verification before concluding.
|
|
120
|
+
* **`PreCompact`**:
|
|
121
|
+
- **Compaction State Reminder**: Reminds the agent to persist unresolved decisions and active task ledgers to disk before context compression.
|
|
122
|
+
* **Universal Native Git Pre-Push Hook** ([`hooks/git/pre-push`](hooks/git/pre-push)):
|
|
123
|
+
- Shell hook installable into any repository (`.git/hooks/pre-push`) that blocks non-fast-forward pushes to `main`/`master` universally across all AI harnesses and terminal users.
|
|
124
|
+
|
|
125
|
+
*(See [Section 6: Full List of Skills & Agents](#6-full-list-of-skills--agents) for detailed skill and persona inventories).*
|
|
126
|
+
|
|
127
|
+
[↑ Back to top](#table-of-contents)
|
|
128
|
+
|
|
129
|
+
---
|
|
130
|
+
|
|
131
|
+
<a id="4-how-to-install"></a>
|
|
132
|
+
## 4. How to Install
|
|
133
|
+
|
|
134
|
+
### Quick Automated Installation (Recommended)
|
|
135
|
+
|
|
136
|
+
Clone the repository and run the setup script with live junctions:
|
|
137
|
+
|
|
138
|
+
```powershell
|
|
139
|
+
# 1. Clone repository
|
|
140
|
+
git clone https://github.com/bepaldes/heimdall-agent.git
|
|
141
|
+
cd heimdall-agent
|
|
142
|
+
|
|
143
|
+
# 2. Bootstrap full ecosystem with live junctions
|
|
144
|
+
node setup.mjs --clean --link --yes
|
|
145
|
+
```
|
|
146
|
+
|
|
147
|
+
> **Interactive Wizard**: Run `node setup.mjs` without flags to interactively select specific AI tools, destination paths, and profiles.
|
|
148
|
+
|
|
149
|
+
### Installation Profiles
|
|
150
|
+
|
|
151
|
+
Select a profile tier based on your machine and workflow needs:
|
|
152
|
+
|
|
153
|
+
| Profile | Skills | Predefined Agents | Description | Best For |
|
|
154
|
+
| :--- | :---: | :---: | :--- | :--- |
|
|
155
|
+
| **`full`** *(Default)* | 56 | 10 | Complete engineering suite: planning, design, security, database, hygiene. | Everyday development across all tools |
|
|
156
|
+
| **`minimal`** | 16 | 4 | Lean core: `orchestrator`, `tester`, `code-sentinel`, `reviewer`. | Lightweight laptops, smaller context windows |
|
|
157
|
+
| **`security`** | 12 | 4 | AppSec suite: `orchestrator`, `security-auditor`, `tester`, `reviewer`. | Penetration testing & pre-deployment audits |
|
|
158
|
+
| **`design`** | 12 | 4 | Frontend & mobile: `orchestrator`, `frontend-designer`, `mobile-designer`, `code-sentinel`. | UI/UX design and design-system work |
|
|
159
|
+
|
|
160
|
+
To deploy a specific profile:
|
|
161
|
+
```powershell
|
|
162
|
+
node setup.mjs --profile minimal --link --clean --yes
|
|
163
|
+
```
|
|
164
|
+
|
|
165
|
+
<a id="supported-tools--runtimes"></a>
|
|
166
|
+
### Supported Tools & Runtimes
|
|
167
|
+
|
|
168
|
+
Heimdall automatically discovers and configures installed AI tools:
|
|
169
|
+
|
|
170
|
+
| Tool | Detection Target | Integration Method |
|
|
171
|
+
| :--- | :--- | :--- |
|
|
172
|
+
| **Claude Code CLI** | `claude` on PATH | Junctions to `~/.claude/skills`, `agents`, `commands`, `hooks` + settings injection |
|
|
173
|
+
| **Google Antigravity** | `agy` on PATH | Junctions to `~/.gemini/skills`, `agents`, and universal `.agents/` |
|
|
174
|
+
| **OpenAI Codex CLI** | `codex` on PATH | Junctions to `~/.codex/skills`, `agents`, and `AGENTS.md` |
|
|
175
|
+
| **Hermes Agent** | `hermes` on PATH / LocalAppData | Junctions to `%LOCALAPPDATA%\hermes\skills` + `external_dirs` in `config.yaml` |
|
|
176
|
+
| **OpenClaw** | `openclaw` on PATH | Junctions to `~/.openclaw/skills` + `AGENTS.md` / `SOUL.md` injection |
|
|
177
|
+
| **OpenDesign** | `open-design` on PATH / `.opendesign` | Automatic visual canvas mode: bypasses Turn 1 grilling gate, preserves `data-od-*` attributes & applies `taste-skill` + `antislop-ui` |
|
|
178
|
+
| **Claude Desktop** | `%APPDATA%\Claude` | Auto-configures Context7 MCP and playbooks in `claude_desktop_config.json` |
|
|
179
|
+
|
|
180
|
+
[↑ Back to top](#table-of-contents)
|
|
181
|
+
|
|
182
|
+
---
|
|
183
|
+
|
|
184
|
+
<a id="5-how-to-use"></a>
|
|
185
|
+
## 5. How to Use (CLI & Slash Commands)
|
|
186
|
+
|
|
187
|
+
### 1. Daily CLI Commands (`heimdall` / `node setup.mjs`)
|
|
188
|
+
|
|
189
|
+
Setup creates a global `heimdall` executable on your PATH (or run `npm link`). `heimdall` and `node setup.mjs` are identical.
|
|
190
|
+
|
|
191
|
+
```powershell
|
|
192
|
+
# 1-second auto-sync after installing a new AI tool (zero file duplication)
|
|
193
|
+
heimdall sync
|
|
194
|
+
|
|
195
|
+
# Audit installed tools, active API endpoints, and skill counts
|
|
196
|
+
heimdall audit
|
|
197
|
+
|
|
198
|
+
# Refresh dynamic model catalog from your active provider/proxy
|
|
199
|
+
heimdall sync-models
|
|
200
|
+
|
|
201
|
+
# Browse canonical skills catalog and upstream repositories
|
|
202
|
+
heimdall skills
|
|
203
|
+
|
|
204
|
+
# Inspect upstream updates and bounded review protocol for skills
|
|
205
|
+
heimdall update-skill ponytail
|
|
206
|
+
heimdall update-skill all
|
|
207
|
+
|
|
208
|
+
# Safely remove Heimdall skills and agent personas across all harnesses
|
|
209
|
+
heimdall uninstall
|
|
210
|
+
```
|
|
211
|
+
|
|
212
|
+
#### CLI Parameter Reference
|
|
213
|
+
|
|
214
|
+
| Flag | Default | Description | Example |
|
|
215
|
+
| :--- | :---: | :--- | :--- |
|
|
216
|
+
| `--profile <name>` | `full` | Skill profile tier: `full`, `minimal`, `security`, or `design`. | `heimdall --profile minimal` |
|
|
217
|
+
| `--agents <targets>` | `all` | Comma-separated list of harnesses: `claude`, `gemini`, `codex`, `desktop`, `all`. | `heimdall --agents claude,gemini` |
|
|
218
|
+
| `--link` | `true` (rec.) | Deploy skills using live NTFS junctions (Windows) or POSIX symlinks (macOS/Linux). | `heimdall --link` |
|
|
219
|
+
| `--clean` | `false` | Wipe legacy skills from target directory before deploying. | `heimdall --clean` |
|
|
220
|
+
| `--dry-run` | `false` | Simulate execution and display actions without modifying the filesystem. | `heimdall --dry-run` |
|
|
221
|
+
| `-y`, `--yes` | `false` | Non-interactive mode (skips wizard prompts). | `heimdall --yes` |
|
|
222
|
+
|
|
223
|
+
---
|
|
224
|
+
|
|
225
|
+
### 2. Using the Orchestrator & Slash Commands
|
|
226
|
+
|
|
227
|
+
The **Orchestrator** is Heimdall's chief engineering coordinator. It interrogates requirements, creates structured plans, dispatches specialized subagents, and enforces verification gates.
|
|
228
|
+
|
|
229
|
+
#### How to Trigger the Orchestrator
|
|
230
|
+
* **In Claude Code CLI**:
|
|
231
|
+
- `/orchestrator <task>` or `/orchestrate <task>`: Launch full orchestration for a task or feature.
|
|
232
|
+
- `/plan <feature>`: Decompose a request into a canonical 7-section plan.
|
|
233
|
+
- `/grill-me`: Interrogate assumptions and explore trade-offs before locking architecture.
|
|
234
|
+
* **In Google Antigravity**:
|
|
235
|
+
- Switch to or mention the `@orchestrator` persona, or type `/plan` / `/grill-me`.
|
|
236
|
+
* **In OpenAI Codex CLI & Hermes**:
|
|
237
|
+
- The universal doctrine in `AGENTS.md` automatically activates Orchestrator discipline for any planning or architectural prompt.
|
|
238
|
+
|
|
239
|
+
#### Orchestration Workflow
|
|
240
|
+
|
|
241
|
+
```mermaid
|
|
242
|
+
flowchart TD
|
|
243
|
+
A["User Request"] --> B["1. Grilling Gate (/grill-me)"]
|
|
244
|
+
B -->|Classify Scope & Probing Questions| C["User Alignment"]
|
|
245
|
+
C --> D["2. Canonical Plan (/plan)"]
|
|
246
|
+
D --> E["3. Subagent Dispatch"]
|
|
247
|
+
E --> F["tester (TDD failing test first)"]
|
|
248
|
+
E --> G["designer (UI & viewport boundaries)"]
|
|
249
|
+
E --> H["code-sentinel (minimal surgical code)"]
|
|
250
|
+
F & G & H --> I["4. Verification & Review"]
|
|
251
|
+
I --> J["Playwright E2E Browser Testing"]
|
|
252
|
+
I --> K["Adversarial Goldfish Code Review"]
|
|
253
|
+
J & K --> L["Complete"]
|
|
254
|
+
```
|
|
255
|
+
|
|
256
|
+
1. **Grilling Gate (Turn 1)**: Classifies scope into the 3-Tier boundary ladder, checks existing code to prevent reinventing the wheel, asks 2–3 probing questions on failure modes, and presents 2 architectural alternatives.
|
|
257
|
+
2. **Canonical Plan (Turn 2)**: Formulates a 7-section canonical plan (`playbooks/05-canonical-plan-template.md`).
|
|
258
|
+
3. **Subagent Execution (Turn 3+)**: The Orchestrator delegates tasks to isolated subagents with specialized briefs.
|
|
259
|
+
4. **Verification & Review**: Mandates automated test execution, Playwright browser E2E verification, and adversarial Goldfish peer review before merge.
|
|
260
|
+
|
|
261
|
+
---
|
|
262
|
+
|
|
263
|
+
### 3. Backlog Management & Plan Lifecycle (Playbook 08)
|
|
264
|
+
|
|
265
|
+
To preserve codebase stability and prevent architectural drift, Heimdall enforces two distinct tracks:
|
|
266
|
+
|
|
267
|
+
#### A. The Four Engineering Flows
|
|
268
|
+
1. **Bugfixes (Fast-Path Loop)**: Receive report -> assess/plan surgical fix -> implement via TDD (failing test first) -> verify with tests & Playwright -> complete.
|
|
269
|
+
2. **New Features (Backlog Intake)**: New requirements are not coded immediately; they are captured in [`docs/backlog.md`](docs/backlog.md) with context and priority.
|
|
270
|
+
3. **Change Request (CR) Analysis Gate**: Backlog items undergo technical impact, blast radius, and dependency analysis. Upon human approval -> author plan -> implement -> verify -> archive.
|
|
271
|
+
4. **Rejection & Postponement**: Discarded or deferred requests return to the backlog with technical rationales or get deleted.
|
|
272
|
+
|
|
273
|
+
#### B. Plan Storage & Archiving Rules
|
|
274
|
+
* **Authoring**: All implementation plans are written to `docs/designs/YYYY-MM-DD <plan-name>.md`.
|
|
275
|
+
* **Archiving**: Once verified and confirmed working, the plan is moved to `docs/designs/old/YYYY-MM-DD <plan-name>.md`.
|
|
276
|
+
|
|
277
|
+
[↑ Back to top](#table-of-contents)
|
|
278
|
+
|
|
279
|
+
---
|
|
280
|
+
|
|
281
|
+
<a id="6-full-list-of-skills--agents"></a>
|
|
282
|
+
## 6. Full List of Skills & Agents
|
|
283
|
+
|
|
284
|
+
<a id="10-predefined-agent-personas"></a>
|
|
285
|
+
<a id="10-predefined-agent-personas"></a>
|
|
286
|
+
### 10 Predefined Agent Personas
|
|
287
|
+
|
|
288
|
+
All personas declare `model: inherit` to run on whichever active model or vendor is configured on your machine without vendor lock-in.
|
|
289
|
+
|
|
290
|
+
| Persona | Capability Tier | Role & Responsibilities | Bound Skills |
|
|
291
|
+
| :--- | :--- | :--- | :--- |
|
|
292
|
+
| **`orchestrator`** | `deep_reasoning` | Planning gatekeeper (`/grill-me`), requirements interrogation, modular task decomposition, Playwright E2E verification enforcement, and subagent coordination. | `brainstorming`, `writing-plans`, `pstack-discipline`, `subagent-driven-development`, `dispatching-parallel-agents`, `using-git-worktrees`, `writing-skills`, `executing-plans`, `herdr` |
|
|
293
|
+
| **`frontend-designer`** | `high_polish_vision` | Enforces design read, typography hierarchy, token mappings, and anti-slop UI aesthetics for web surfaces. | `taste-skill`, `brandkit`, `minimalist-skill`, `brutalist-skill`, `soft-skill`, `antislop-ui`, `antislop-human`, `stitch-skill`, `image-to-code-skill`, `imagegen-frontend-web`, `redesign-skill` |
|
|
294
|
+
| **`mobile-designer`** | `responsive_flex_safety` | Mobile viewport safety (320px–430px), 48px touch targets, zero-clipping overflow flex containers, and responsive assets. | `antislop-layoutmobile`, `antislop-human`, `antislop-ui`, `imagegen-frontend-mobile`, `taste-skill` |
|
|
295
|
+
| **`tester`** | `fast_verification` | Enforces strict Test-Driven Development (TDD) and browser verification (Playwright). Rejects pseudo-verification (`curl`, `grep`, `tsc`). | `test-driven-development`, `verification-before-completion`, `systematic-debugging`, `executing-plans` |
|
|
296
|
+
| **`security-auditor`** | `deep_assurance_audit` | Dynamic differential HTTP probing across auth levels, OWASP Top 10 defenses, and Trail of Bits insecure defaults detection. | `strix-security`, `security-audit-sweep`, `owasp-security`, `cloudflare-security-audit`, `snyk-agent-scan`, `trailofbits-audit-context`, `trailofbits-insecure-defaults`, `trailofbits-triage-brocards` |
|
|
297
|
+
| **`database-architect`** | `schema_migration_safety` | Governs non-destructive migrations, normalization, query plan audits (`EXPLAIN ANALYZE`), and connection pooling (Postgres/Supabase, SQLite, MySQL). | `postgres-best-practices`, `systematic-debugging`, `karpathy-guidelines` |
|
|
298
|
+
| **`code-sentinel`** | `surgical_restraint` | Karpathy simplicity: writes minimal surgical code, strips boilerplate comments, purges defensive dead code, and enforces anti-slop standards. | `karpathy-guidelines`, `clean-code`, `ponytail`, `antislop`, `antislop-code`, `antislop-copywriting`, `antislop-human`, `finishing-a-development-branch` |
|
|
299
|
+
| **`reviewer`** | `adversarial_diff_eval` | Performs adversarial diff analysis, catches silent regressions and swallowed errors, executes thermo maintainability reviews, and coordinates cross-model validation reviews. | `communication-doctrine`, `thermo`, `requesting-code-review`, `receiving-code-review`, `claude-collaborator`, `gemini-collaborator`, `codex-collaborator`, `using-superpowers`, `diagnosing-superpowers`, `output-skill` |
|
|
300
|
+
| **`modernizer`** | `legacy_migration_safety` | Executes legacy codebase transformations, runtime upgrades, and Strangler Fig migrations guarded by Golden Master characterization tests. | `test-driven-development`, `verification-before-completion`, `systematic-debugging`, `karpathy-guidelines`, `project-hygiene`, `output-skill` |
|
|
301
|
+
| **`cloud-engineer`** | `infra_container_safety` | Governs containerization (Docker, Compose), Kubernetes manifests, Infrastructure as Code (Terraform), reverse proxies (Caddy, Nginx), CI/CD automation, and terminating verification. | `communication-doctrine`, `karpathy-guidelines`, `clean-code`, `systematic-debugging`, `project-hygiene`, `progressive-disclosure` |
|
|
302
|
+
|
|
303
|
+
---
|
|
304
|
+
|
|
305
|
+
<a id="skill-inventory-56-modules-across-24-toolkits"></a>
|
|
306
|
+
### Skill Inventory (56 Modules Across 24 Toolkits)
|
|
307
|
+
|
|
308
|
+
Heimdall organizes capabilities into **5 Core Multi-Skill Suites (37 modules)** and **19 Standalone Toolkits (19 modules)**:
|
|
309
|
+
|
|
310
|
+
#### Core Multi-Skill Suites (5 Suites / 37 Modules)
|
|
311
|
+
|
|
312
|
+
<details open>
|
|
313
|
+
<summary><b>1. Superpowers Engineering Suite (15 modules) — Jesse Vincent / obra</b></summary>
|
|
314
|
+
|
|
315
|
+
- `brainstorming`: Surfaces implicit assumptions and explores alternatives before design lock.
|
|
316
|
+
- `writing-plans`: Structures modular, bite-sized tasks with verifiable completion criteria.
|
|
317
|
+
- `executing-plans`: Enforces step-by-step verification and halts execution upon unexpected failures.
|
|
318
|
+
- `subagent-driven-development`: Decomposes large tasks into isolated subagents with specialized briefs.
|
|
319
|
+
- `dispatching-parallel-agents`: Coordinates concurrent subagent workers on independent branches.
|
|
320
|
+
- `test-driven-development`: Requires failing automated tests prior to implementation logic.
|
|
321
|
+
- `systematic-debugging`: Isolates root causes using scientific hypothesis testing and build triage heuristics.
|
|
322
|
+
- `verification-before-completion`: Mandates passing test suites and live verification before claiming completion.
|
|
323
|
+
- `finishing-a-development-branch`: Verifies branch hygiene, tests, and documentation before merge.
|
|
324
|
+
- `using-git-worktrees`: Manages parallel agent execution branches without dirtying working trees.
|
|
325
|
+
- `requesting-code-review`: Formats structured diff context for adversarial peer review.
|
|
326
|
+
- `receiving-code-review`: Parses peer critiques objectively and implements verified recommendations.
|
|
327
|
+
- `using-superpowers`: Multi-agent operational playbook for complex software development.
|
|
328
|
+
- `diagnosing-superpowers`: Health check and triage harness for agent tooling and skill resolution.
|
|
329
|
+
- `writing-skills`: Authors new modular skills adhering to standard frontmatter and trigger contracts.
|
|
330
|
+
|
|
331
|
+
</details>
|
|
332
|
+
|
|
333
|
+
<details>
|
|
334
|
+
<summary><b>2. Taste Design & Aesthetic Studio (10 modules)</b></summary>
|
|
335
|
+
|
|
336
|
+
- `taste-skill`: Enforces cohesive design reads, purpose-driven typography, and brand-first color logic.
|
|
337
|
+
- `brandkit`: Manages design tokens, invariant brand assets, and multi-palette themes.
|
|
338
|
+
- `brutalist-skill`: High-contrast, bold typographic layouts with deliberate structural tension.
|
|
339
|
+
- `minimalist-skill`: Ultra-clean editorial layouts emphasizing typography, space, and restraint.
|
|
340
|
+
- `soft-skill`: Tactile micro-interactions, subtle elevation, and organic surface transitions.
|
|
341
|
+
- `redesign-skill`: Systematic visual elevation of legacy interfaces without breaking existing logic.
|
|
342
|
+
- `image-to-code-skill`: High-fidelity translation from visual wireframes/mockups to component code.
|
|
343
|
+
- `stitch-skill`: Cross-component layout integration and responsive flow alignment.
|
|
344
|
+
- `imagegen-frontend-web`: Web-optimized visual asset generation and placeholder authoring.
|
|
345
|
+
- `imagegen-frontend-mobile`: Mobile-native aspect ratio and resolution image scaffolding.
|
|
346
|
+
|
|
347
|
+
</details>
|
|
348
|
+
|
|
349
|
+
<details>
|
|
350
|
+
<summary><b>3. Anti-Slop Quality Suite (6 modules) — Jesse Vincent / obra</b></summary>
|
|
351
|
+
|
|
352
|
+
- `antislop`: Core guardrail prohibiting generic AI filler, fake buzzwords, and decorative bloat.
|
|
353
|
+
- `antislop-code`: Prohibits redundant comments, defensive dead code, and speculative abstractions.
|
|
354
|
+
- `antislop-copywriting`: Bans AI buzzwords (*unlock, elevate, robust*), signposting, and fake authority tropes.
|
|
355
|
+
- `antislop-ui`: Rejects generic purple gradients, uniform pill radius, and unmotivated dark modes.
|
|
356
|
+
- `antislop-human`: Enforces WCAG AAA contrast, semantic HTML, and accessible interactive targets.
|
|
357
|
+
- `antislop-layoutmobile`: Guarantees responsive flex safety, zero clipping, and touch-target padding.
|
|
358
|
+
|
|
359
|
+
</details>
|
|
360
|
+
|
|
361
|
+
<details>
|
|
362
|
+
<summary><b>4. Tri-Directional Cross-Model Bridges (3 modules)</b></summary>
|
|
363
|
+
|
|
364
|
+
- `claude-collaborator`: Cross-model delegation bridge to Claude Opus / Sonnet for deep architectural review.
|
|
365
|
+
- `gemini-collaborator`: Cross-model delegation bridge to Google Antigravity / Gemini for high-velocity scans.
|
|
366
|
+
- `codex-collaborator`: Cross-model delegation bridge to OpenAI Codex CLI for adversarial peer reviews.
|
|
367
|
+
|
|
368
|
+
</details>
|
|
369
|
+
|
|
370
|
+
<details>
|
|
371
|
+
<summary><b>5. Trail of Bits High-Assurance AppSec Suite (3 modules) — Trail of Bits</b></summary>
|
|
372
|
+
|
|
373
|
+
- `trailofbits-audit-context`: High-assurance code assumption, guarantee, and architectural dependency mapping.
|
|
374
|
+
- `trailofbits-insecure-defaults`: Detection of insecure default configurations, fail-open patterns, and permissive access.
|
|
375
|
+
- `trailofbits-triage-brocards`: Systematic evaluation of incoming vulnerability reports against 7 principled brocards.
|
|
376
|
+
|
|
377
|
+
</details>
|
|
378
|
+
|
|
379
|
+
#### Standalone Toolkits (19 Curated Toolkits / 19 Modules)
|
|
380
|
+
|
|
381
|
+
<details open>
|
|
382
|
+
<summary><b>Browse Standalone Toolkits</b></summary>
|
|
383
|
+
|
|
384
|
+
- **`thermo`**: Uncompromising architectural and maintainability review focusing on "Code Judo" structural simplification, spaghetti conditional elimination, and modularity health.
|
|
385
|
+
- **`pstack-discipline`**: High-rigor engineering discipline from the pstack / poteto framework: "Prove It Works", "Fix Root Causes", "Test Behavior, Not Implementation", and "Subtract Before You Add".
|
|
386
|
+
- **`communication-doctrine`**: Bottom Line Up Front (BLUF) and Simplified Technical English (STE) communication doctrine for AI agents, implementation plans, code reviews, and subagent handoffs.
|
|
387
|
+
- **`threat-modeling`**: Systematic STRIDE threat modeling, trust boundary mapping, and mitigation verification for architecture, API, and cloud infrastructure changes.
|
|
388
|
+
- **`mcp-engineering`**: Standards, JSON-RPC 2.0 protocol compliance, schema validation, and stdio/SSE transport discipline for authoring Model Context Protocol (MCP) servers and tools.
|
|
389
|
+
- **`herdr`**: Control Herdr, a terminal workspace manager for coding agents. Inspect or control panes, tabs, workspaces, commands, or coordinate with peer agents in persistent terminal sessions.
|
|
390
|
+
- **`clean-code` (`ub-mode`)**: Robert C. "Uncle Bob" Martin's disciplined Clean Code engineering standard. Enforces TDD cycles, laziness protocol, premise interrogation, boundary discipline, and mathematical complexity gates (CRAP < 10, DRY similarity < 0.8, mutant-killing test design).
|
|
391
|
+
- **`ponytail`**: Pragmatic senior developer discipline. Enforces Dietrich Gebert's Decision Ladder: YAGNI checks, codebase reuse, built-in standard library, native platform features, and zero premature abstractions.
|
|
392
|
+
- **`karpathy-guidelines`**: Andrej Karpathy's simplicity heuristics: write minimal surgical code, reject speculative configurability, surface hidden assumptions, and never touch adjacent working code.
|
|
393
|
+
- **`caveman`**: Julius Brussee's token-reduction protocol slashing conversational ceremony while preserving raw code, shell commands, and structured diffs.
|
|
394
|
+
- **`strix-security`**: Autonomous dynamic HTTP differential probing across Anonymous, Unprivileged, and Privileged identity contexts.
|
|
395
|
+
- **`security-audit-sweep`**: 4-phase security audit sweeping route gates, IAM entitlement least-privilege, dependency vulnerabilities, and secret leakage.
|
|
396
|
+
- **`owasp-security`**: Hardens code against OWASP Top 10:2025, ASVS 5.0, LLM Top 10, and Agentic Application risks.
|
|
397
|
+
- **`cloudflare-security-audit`**: Edge security, WAF configuration, and CORS boundary enforcement.
|
|
398
|
+
- **`snyk-agent-scan`**: Automated scanning of AI skills, MCP configurations, and supply chains for prompt injection and credential leaks.
|
|
399
|
+
- **`postgres-best-practices`**: Supabase-curated architectural guidelines for PostgreSQL schema design, indexing, connection pooling, and RLS policies.
|
|
400
|
+
- **`progressive-disclosure`**: Anthropic & Google-aligned 3-layer progressive disclosure standard cutting prompt overhead by >80% and preventing subagent sprawl.
|
|
401
|
+
- **`project-hygiene`**: Sweeps workspaces for dead code, unused exports, circular dependencies, and stale build caches.
|
|
402
|
+
- **`output-skill`**: Guarantees unabridged LLM output without ellipses (`...`), incomplete code blocks, or truncation.
|
|
403
|
+
|
|
404
|
+
</details>
|
|
405
|
+
|
|
406
|
+
[↑ Back to top](#table-of-contents)
|
|
407
|
+
|
|
408
|
+
---
|
|
409
|
+
|
|
410
|
+
<a id="7-additional-companion-tools"></a>
|
|
411
|
+
## 7. Additional Companion Tools
|
|
412
|
+
|
|
413
|
+
For multi-device pair programming, mobile monitoring, and project memory, Heimdall integrates with:
|
|
414
|
+
|
|
415
|
+
* **[Herdr (`herdr.dev`)](https://herdr.dev/)**: Terminal-native agent multiplexer written in Rust. Keeps background agent sessions persistent across connection drops and tracks status (`working`, `blocked`, `idle`).
|
|
416
|
+
* **[OpenDesign (`open-design.ai`)](https://open-design.ai/)**: Local-first, open-source AI visual design canvas workspace. Spawns Claude Code, Codex, and Gemini CLI as runtime adapters; Heimdall's visual canvas contract exempts canvas generation from Turn 1 grilling gates while enforcing `taste-skill`, WCAG AAA accessibility, and `data-od-*` DOM layer preservation.
|
|
417
|
+
* **[Moshi (`getmoshi.app`)](https://getmoshi.app/)**: Mobile client (iOS/Android) pairing with your terminal session. Delivers push notifications when an agent hits an interactive planning gate and enables remote approval.
|
|
418
|
+
* **[Graphify (`github.com/Graphify-Labs/graphify`)](https://github.com/Graphify-Labs/graphify)**: Local-first code knowledge graph builder. Uses Tree-sitter AST parsing across 40+ programming languages to build deterministic dependency maps with zero LLM API costs, exporting directly to Obsidian vaults.
|
|
419
|
+
* **[Obsidian (`obsidian.md`)](https://obsidian.md/)**: Local-first Markdown knowledge base. Paired with Graphify-generated vaults (`[[wikilinks]]`), it serves as persistent external memory for AI coding agents, loading immediate architectural context on startup without token-heavy scanning.
|
|
420
|
+
|
|
421
|
+
[↑ Back to top](#table-of-contents)
|
|
422
|
+
|
|
423
|
+
---
|
|
424
|
+
|
|
425
|
+
<a id="license"></a>
|
|
426
|
+
## License
|
|
427
|
+
|
|
428
|
+
MIT © [Bernardo Paldes](https://github.com/bepaldes)
|
|
429
|
+
|
|
430
|
+
[↑ Back to top](#table-of-contents)
|