Reuse
Borrowing it
Nothing to install: this file belongs to GeoffGodwin/tekhton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GeoffGodwin/tekhton/main/CLAUDE.mdgit clone --depth 1 https://github.com/GeoffGodwin/tekhtonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/geoffgodwin/tekhton/claude-md)<a href="https://agentmods.dev/instructions/geoffgodwin/tekhton/claude-md"><img src="https://agentmods.dev/badge/instructions/geoffgodwin/tekhton/claude-md.svg" alt="Measured on agentmods" height="20"></a> Per session 10,570 This file is loaded in full into every session.
When invoked 10,570 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.10570 | $0.10570 |
| Opus 5 | $0.05285 | $0.05285 |
| Sonnet 5 | $0.02114 | $0.02114 |
| Haiku 4.5 | $0.01057 | $0.01057 |
Security
Grade A, and why
tekhton CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
CLAUDE.md · 585 lines
How it starts
The opening of the file, as written. The whole thing — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tekhton — Project Configuration
What This Is
Tekhton is a standalone, project-agnostic multi-agent development pipeline built on the Claude CLI. It orchestrates a Pre-flight → Intake → Scout → Coder → Security → Reviewer → Tester cycle with automatic rework routing, build gates, state persistence, and resume support.
One intent. Many hands.
Repository Layout
tekhton/
├── tekhton.sh # Main entry point
├── lib/ # Shared libraries (sourced by tekhton.sh)
│ ├── common.sh # Colors, logging, prerequisite checks
│ ├── config.sh # Config loader + validation
│ ├── config_defaults.sh # Default values for all config keys
│ ├── config_defaults_ci.sh # M138 runtime CI environment auto-detection helpers
│ ├── agent.sh # Agent wrapper, metrics, run_agent()
│ ├── agent_helpers.sh # Agent invocation helpers
│ ├── agent_monitor.sh # Agent monitoring, activity detection, process management
│ ├── agent_monitor_helpers.sh # Monitor support functions
│ ├── agent_monitor_platform.sh # Platform-specific monitor code
│ ├── agent_retry.sh # Transient error retry logic
│ ├── agent_retry_pause.sh # M124 spinner pause/resume bracket for enter_quota_pause
│ ├── gates.sh # Build gate + completion gate
│ ├── hooks.sh # Archive, commit message, final checks
│ ├── finalize.sh # Hook-based finalization sequence
│ ├── finalize_commit.sh # Commit hook + _do_git_commit helpers
│ ├── finalize_aux.sh # Aux finalize hooks (express, baseline, M129 reset)
│ ├── finalize_dashboard_hooks.sh # Dashboard/causal-log/TUI finalize hooks
│ ├── finalize_display.sh # Completion banner + action items
│ ├── finalize_summary.sh # RUN_SUMMARY.json emitter
│ ├── finalize_summary_collectors.sh # M132 RUN_SUMMARY enrichment collectors (causal/build-fix/recovery/preflight-ui)
│ ├── finalize_version.sh # Project version bump finalize hooks
│ ├── project_version.sh # Target-project version file detection
│ ├── project_version_bump.sh # Version bump logic + file writes
│ ├── notes.sh # Human notes management
│ ├── prompts.sh # Template engine for .prompt.md files
│ ├── state.sh # Pipeline state persistence + resume
│ ├── turns.sh # Turn-exhaustion continuation logic
│ ├── drift.sh # Drift log, ADL, human action management
│ ├── drift_artifacts.sh # Drift artifact processing
│ ├── drift_cleanup.sh # Non-blocking log cleanup
│ ├── docs_agent.sh # Docs agent skip-path detection + public-surface parsing
│ ├── detect.sh # Tech stack detection engine
│ ├── detect_commands.sh # Build/test/lint command detection
│ ├── detect_report.sh # Detection report formatter
│ ├── plan.sh # Planning phase orchestration + config
│ ├── plan_completeness.sh # Design doc structural validation
│ ├── plan_state.sh # Planning state persistence + resume
│ ├── replan.sh # Replan orchestration
│ ├── replan_brownfield.sh # Brownfield replan with codebase summary
│ ├── replan_midrun.sh # Mid-run replan trigger
│ ├── context.sh # Token accounting + context compiler
│ ├── context_budget.sh # Context budget checking
│ ├── context_compiler.sh # Task-scoped context assembly
│ ├── milestones.sh # Milestone state machine + acceptance checking
│ ├── milestone_ops.sh # Milestone marking + disposition
│ ├── milestone_acceptance.sh # Milestone acceptance criteria checking
│ ├── milestone_acceptance_lint.sh # Acceptance criteria quality linter
│ ├── milestone_archival.sh # Milestone archival to MILESTONE_ARCHIVE.md
│ ├── milestone_metadata.sh # Milestone metadata HTML comments
│ ├── milestone_split.sh # Pre-flight milestone splitting
│ ├── milestone_split_dag.sh # DAG-mode splitting: file read + array splice
│ ├── milestone_split_nullrun.sh # Null-run auto-split handler
│ ├── orchestrate.sh # Outer orchestration loop (--complete)
│ ├── orchestrate_helpers.sh # Orchestration support functions
│ ├── orchestrate_state_save.sh # _save_orchestration_state + recovery-block glue
│ ├── orchestrate_recovery.sh # Failure classification + recovery
│ ├── orchestrate_recovery_causal.sh # M130 causal-context loader + retry guards
│ ├── orchestrate_recovery_print.sh # M94/M130 inline recovery block printer
│ ├── clarify.sh # Clarification protocol + replan trigger
│ ├── specialists.sh # Specialist review framework
│ ├── metrics.sh # Run metrics collection + adaptive calibration
│ ├── metrics_calibration.sh # Adaptive turn calibration
│ ├── errors.sh # Error taxonomy, classification + reporting
│ ├── errors_helpers.sh # Error classification helpers
│ ├── milestone_dag.sh # Milestone DAG infrastructure + manifest parser
│ ├── milestone_dag_migrate.sh # Inline→file milestone migration
│ ├── milestone_window.sh # Character-budgeted milestone sliding window
│ ├── draft_milestones.sh # Interactive milestone authoring flow (--draft-milestones)
│ ├── draft_milestones_write.sh # Validation and manifest writing for draft milestones
│ ├── milestone_progress.sh # Milestone progress CLI + next-action guidance
│ ├── milestone_progress_helpers.sh # Rendering helpers for milestone progress
│ ├── indexer.sh # Repo map orchestration + Python tool invocation
│ ├── indexer_audit.sh # Startup grammar audit (M123)
│ ├── indexer_helpers.sh # Language detection, config validation, file extraction
│ ├── indexer_history.sh # Task→file association tracking (JSONL)
│ ├── causality.sh # Causal event log infrastructure + query layer
│ ├── causality_query.sh # Causal log query helpers
│ ├── test_audit.sh # Test integrity audit orchestration
│ ├── test_audit_helpers.sh # Pre-audit file collection + context assembly
│ ├── test_audit_detection.sh # Shell-based orphan + weakening detection
│ ├── test_audit_verdict.sh # Audit verdict parsing + routing
│ ├── test_audit_symbols.sh # Symbol-level stale reference detection (M88)
│ ├── test_baseline.sh # Test baseline capture + pre-existing failure detection
│ ├── test_dedup.sh # Test run deduplication via working-tree fingerprint (M105)
│ ├── mcp.sh # MCP server lifecycle management (Serena)
│ ├── health.sh # Project health scoring orchestration
│ ├── health_checks.sh # Health check implementations
│ ├── health_checks_infra.sh # Infrastructure health checks
│ ├── health_checks_hygiene.sh # Project hygiene health check
│ ├── dashboard.sh # Watchtower dashboard data emission
│ ├── dashboard_emitters.sh # Dashboard data file writers
│ ├── dashboard_parsers.sh # Dashboard data parsers
│ ├── diagnose.sh # Pipeline diagnostics engine
│ ├── diagnose_helpers.sh # Diagnostic helper functions
│ ├── diagnose_output.sh # Diagnostic output formatting (writer, report)
│ ├── diagnose_output_extra.sh # Crash first-aid + dashboard-diagnosis (M129)
│ ├── diagnose_rules.sh # Diagnostic rule definitions
│ ├── diagnose_rules_extra.sh # Secondary diagnostic rules
│ ├── diagnose_rules_migration.sh # Migration & version-mismatch rules
│ ├── diagnose_rules_resilience.sh # M133 resilience-arc primary rules
│ ├── diagnose_rules_resilience_preflight.sh # M131/M133 preflight-config rule (extracted)
│ ├── failure_context.sh # M129 primary/secondary cause slot helpers
│ ├── express.sh # Express mode (zero-config execution)
│ ├── express_persist.sh # Express mode configuration persistence
│ ├── dry_run.sh # Dry-run preview mode
│ ├── init.sh # Init orchestration
│ ├── init_config.sh # Init config generation
│ ├── init_config_emitters.sh # Init config section emitters
│ ├── init_config_sections.sh # Init config section builders
│ ├── init_config_workspace.sh # Init config workspace/service section emitter
│ ├── init_helpers.sh # Init helper functions
│ ├── init_report.sh # Init report generation
│ ├── init_wizard.sh # Init feature wizard (M109: Python feature prompts)
│ ├── init_synthesize_helpers.sh # Init synthesis helpers
│ ├── init_synthesize_ui.sh # Init synthesis UI
│ ├── intake_helpers.sh # Intake agent helpers
│ ├── intake_verdict_handlers.sh # Intake verdict routing
│ ├── migrate.sh # Version migration framework
│ ├── migrate_cli.sh # Migration CLI interface
│ ├── notes_core.sh # Notes core rewrite
│ ├── notes_core_normalize.sh # Markdown blank-line normalization helper
│ ├── pipeline_order.sh # Configurable pipeline stage ordering (PIPELINE_ORDER config key)
│ ├── pipeline_order_policy.sh # M110 policy, metrics key resolution, and stage plan helpers — sourced by pipeline_order.sh
│ ├── notes_cli.sh # Notes CLI subcommand
│ ├── notes_cli_write.sh # Notes CLI write operations
│ ├── notes_cleanup.sh # Notes cleanup operations
│ ├── notes_acceptance.sh # Notes acceptance checking
│ ├── notes_acceptance_helpers.sh # Notes acceptance helpers
│ ├── notes_migrate.sh # Notes format migration
│ ├── notes_rollback.sh # Notes rollback support
│ ├── context_cache.sh # Intra-run context cache
│ ├── checkpoint.sh # Progress checkpoint management
│ ├── checkpoint_display.sh # Checkpoint display formatting
│ ├── crawler.sh # Project crawler orchestration
│ ├── crawler_content.sh # Crawler content sampling
│ ├── crawler_inventory.sh # Crawler file inventory
│ ├── crawler_deps.sh # Crawler dependency analysis
│ ├── rescan.sh # Incremental rescan
│ ├── rescan_helpers.sh # Rescan helper functions
│ ├── artifact_handler.sh # AI artifact detection handler
│ ├── artifact_handler_ops.sh # Artifact handler operations
│ ├── detect_services.sh # Service detection
│ ├── detect_workspaces.sh # Workspace detection
│ ├── detect_ci.sh # CI/CD detection
│ ├── detect_infrastructure.sh # Infrastructure detection
│ ├── detect_test_frameworks.sh # Test framework detection
│ ├── detect_doc_quality.sh # Documentation quality assessment
│ ├── detect_ai_artifacts.sh # AI artifact detection
│ ├── inbox.sh # Inbox management
│ ├── plan_answers.sh # Planning answer file import
│ ├── plan_browser.sh # Browser-based planning
│ ├── plan_review.sh # Planning review UI
│ ├── safety_net.sh # Run safety net + rollback
│ ├── run_memory.sh # Structured cross-run memory (JSONL)
│ ├── timing.sh # Stage timing and duration estimation
│ ├── milestone_dag_helpers.sh # DAG helper functions
│ ├── milestone_dag_io.sh # DAG I/O operations
│ ├── milestone_dag_validate.sh # DAG validation
│ ├── milestone_archival_helpers.sh # Archival helper functions
│ ├── metrics_dashboard.sh # Metrics dashboard formatting
│ ├── drift_prune.sh # Drift log pruning
│ ├── quota.sh # API quota management
│ ├── quota_sleep.sh # M124 chunked-sleep helper for enter_quota_pause
│ ├── quota_probe.sh # M125 layered probe (version/zero_turn/fallback) + back-off/jitter helpers
│ ├── error_patterns.sh # Error pattern registry + classification engine
│ ├── error_patterns_classify.sh # M127 confidence-based mixed-log classifier + routing decision
│ ├── preflight.sh # Pre-flight environment validation
│ ├── preflight_checks_ui.sh # M131 UI test framework config audit (Playwright/Cypress/Jest/Vitest)
│ ├── tui.sh # M97 TUI sidecar manager (spawn/stop/update calls)
│ ├── tui_helpers.sh # M97 JSON builders for tui_status.json
│ ├── tui_ops.sh # M104 run_op wrapper + TUI update/event helpers; run_op uses M113 substage API (M115)
│ ├── tui_ops_pause.sh # M124 quota-pause TUI API (tui_enter/update/exit_pause)
│ ├── tui_ops_substage.sh # M113 hierarchical substage API (tui_substage_begin/end)
│ └── tui_liveness.sh # Atomic status-file writer + sampled sidecar liveness probe
├── stages/ # Stage implementations (sourced by tekhton.sh)
│ ├── architect.sh # Pre-stage: Architect audit (conditional)
│ ├── intake.sh # Task intake / PM gate
│ ├── coder.sh # Scout + Coder + build gate
│ ├── coder_buildfix.sh # M127 routing + M128 build-fix continuation loop (sub-stage)
│ ├── coder_buildfix_helpers.sh # M128 pure helpers (budget, progress signal, report writer, stats export)
│ ├── docs.sh # Docs agent stage (optional, Haiku-powered)
│ ├── security.sh # Security review stage
│ ├── review.sh # Review loop + rework routing
│ ├── tester.sh # Test writing + validation
│ ├── tester_tdd.sh # TDD phase orchestration
│ ├── tester_continuation.sh # Turn-exhaustion continuation logic
│ ├── tester_fix.sh # Test failure fix orchestration
│ ├── tester_timing.sh # Tester timing and duration estimation
│ ├── tester_validation.sh # Post-tester output validation and routing
│ ├── cleanup.sh # Post-success debt sweep stage
│ ├── init_synthesize.sh # Init synthesis stage
│ ├── plan_interview.sh # Planning: interactive interview agent
│ ├── plan_followup_interview.sh # Planning: follow-up interview agent
│ └── plan_generate.sh # Planning: CLAUDE.md generation agent
├── prompts/ # Prompt templates with {{VAR}} substitution
│ ├── architect.prompt.md
│ ├── architect_sr_rework.prompt.md
│ ├── architect_jr_rework.prompt.md
│ ├── architect_review.prompt.md
│ ├── coder.prompt.md
│ ├── coder_rework.prompt.md
│ ├── jr_coder.prompt.md
│ ├── reviewer.prompt.md
│ ├── scout.prompt.md
│ ├── tester.prompt.md
│ ├── tester_resume.prompt.md
│ ├── build_fix.prompt.md
│ ├── build_fix_minimal.prompt.md
│ ├── analyze_cleanup.prompt.md
│ ├── seed_contracts.prompt.md
│ ├── milestone_split.prompt.md # Milestone splitting prompt
│ ├── plan_interview.prompt.md # Planning interview system prompt
│ ├── plan_interview_followup.prompt.md # Planning follow-up interview prompt
│ ├── plan_generate.prompt.md # CLAUDE.md generation prompt
│ ├── cleanup.prompt.md # Debt sweep agent prompt
│ ├── docs_agent.prompt.md # Docs agent prompt (M75)
│ ├── replan.prompt.md # Brownfield replan prompt
│ ├── clarification.prompt.md # Clarification integration prompt
│ ├── specialist_security.prompt.md # Security review prompt
│ ├── specialist_performance.prompt.md # Performance review prompt
│ ├── specialist_api.prompt.md # API contract review prompt
│ └── draft_milestones.prompt.md # Interactive milestone authoring prompt
├── templates/ # Templates copied into target projects by --init
│ ├── pipeline.conf.example
│ ├── coder.md
│ ├── reviewer.md
│ ├── tester.md
│ ├── jr-coder.md
│ └── architect.md
├── templates/plans/ # Design doc templates by project type
│ ├── web-app.md
│ ├── web-game.md
│ ├── cli-tool.md
│ ├── api-service.md
│ ├── mobile-app.md
│ ├── library.md
│ └── custom.md
├── tools/ # Python tooling (optional dependency)
│ ├── repo_map.py # Tree-sitter repo map generator + PageRank
│ ├── tag_cache.py # Disk-based tag cache with mtime tracking
│ ├── tree_sitter_languages.py # Language detection + grammar loading
│ ├── requirements.txt # Pinned Python dependencies
│ ├── setup_indexer.sh # Indexer virtualenv setup script
│ ├── setup_serena.sh # Serena MCP server setup script
│ ├── serena_config_template.json # MCP config template
│ ├── tui.py # TUI sidecar main — rich.live loop + layout assembly
│ ├── tui_render.py # TUI render helpers — logo, header bar, stage pills, events
│ ├── tui_render_pause.py # M124 quota-pause active-bar renderer
│ ├── tui_hold.py # TUI hold-on-complete — final event log dump + Enter wait
│ └── tests/ # Python unit tests
│ ├── conftest.py
│ ├── test_repo_map.py
│ ├── test_tag_cache.py
│ ├── test_history.py
│ ├── test_tree_sitter_languages.py
│ ├── test_extract_tags_integration.py
│ └── test_tui.py # TUI sidecar renderer tests
├── platforms/ # Platform-specific UI knowledge (M57–M60)
│ ├── _base.sh # Platform resolution + universal helpers
│ ├── _universal/ # Cross-platform UI guidance (always included)
│ ├── web/ # Web: React, Vue, Svelte, Angular, HTML
│ ├── mobile_flutter/ # Flutter/Dart
│ ├── mobile_native_ios/ # Swift/SwiftUI/UIKit
│ ├── mobile_native_android/ # Kotlin/Jetpack Compose
│ └── game_web/ # Phaser, PixiJS, Three.js, Babylon.js
├── tests/ # Self-tests
│ └── fixtures/indexer_project/ # Multi-language fixture project
└── examples/ # Sample dependency constraint validation scripts
├── architecture_constraints.yaml # Sample constraint manifest
├── check_imports_dart.sh # Dart/Flutter import validator
├── check_imports_python.sh # Python import validator
└── check_imports_typescript.sh # TypeScript/JS import validator
Changes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 585 lines · 10,570 tokens per session scan A 1f6072635375
tekhton CLAUDE.md is an instructions file published in the GitHub repository GeoffGodwin/tekhton (5 stars, last pushed 2mo ago), licensed MIT. It adds 10,570 tokens to every session, about $0.0528 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Related
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.