Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/alexander-akhmetov/programmator/claude-mdgit clone --depth 1 https://github.com/alexander-akhmetov/programmatorWrote 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/alexander-akhmetov/programmator/claude-md)<a href="https://agentmods.dev/instructions/alexander-akhmetov/programmator/claude-md"><img src="https://agentmods.dev/badge/instructions/alexander-akhmetov/programmator/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
programmator 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 5d 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.
What it actually says
CLAUDE.md
Build & Test
go build ./... # Build
go test ./... # All tests
go test ./internal/parser # Single package
go test -race ./... # Race detector (CI uses this)
make lint # golangci-lint + govulncheck + deadcode + go mod tidy
make fmt # Auto-fix formatting
Code Conventions
- Tests use
stretchr/testify. Prefer test cases pattern to reuse setup and verification. - Dependencies vendored in
vendor/. - CI runs
go test -raceandgolangci-lint.
Package Layout
Entry: cmd/programmator/main.go → internal/cli/ → internal/loop/loop.go
internal/loop/— main orchestration loopinternal/llm/— executor interface and shared utilities; sub-packagesclaude/,pi/,opencode/,codex/for each executor;executor/factoryinternal/source/— work source abstraction (PlanSource, TicketSource), auto-detection indetect.gointernal/review/— multi-agent review pipeline, parallel execution, validatorsinternal/parser/— PROGRAMMATOR_STATUS YAML extraction from executor outputinternal/prompt/— Gotext/templateprompt builder with embedded/global/local fallbackinternal/config/— YAML config with multi-level merge; defaults ininternal/config/defaults/internal/domain/— core types (WorkItem, Phase)internal/protocol/— cross-package constants (status values, source types)internal/event/— typed event system for loop ↔ CLI communicationinternal/safety/— exit conditions (max iterations, stagnation, error repetition)internal/git/— git operations wrapper for auto-commit workflowinternal/dirs/— XDG paths (ConfigDir, StateDir, LogsDir)internal/ticket/— externalticketCLI wrapper; mock inclient_mock.gointernal/plan/— plan file parser with checkbox tasks and validation commands
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.
- 5d ago First seen · 39 lines · 479 tokens per session scan A 8d0c5408b671
programmator CLAUDE.md is an instructions file published in the GitHub repository alexander-akhmetov/programmator (2 stars, last pushed 3mo ago), licensed MIT. It adds 479 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
ralphctl CLAUDE.md
Claude Code instructions for wcygan/ralphctl, covering claude.md, project overview, build & test, cli commands and dependencies.
rooda AGENTS.md
AGENTS.md instructions for jomadu/rooda, covering agent instructions, issue tracking, quick reference, landing the plane (session completion) and work tracking system.
ClawAI CLAUDE.md
Claude Code instructions for ihabkhaled/ClawAI, covering clawai — root policy, identity, authority hierarchy (higher wins on conflict), first command, always and work arriving as a document.
ai-assistant-instructions CLAUDE.md
Claude Code instructions for dryvist/ai-assistant-instructions: Canonical agent instructions live in AGENTS.md and agentsmd/rules/. Nix-managed machines auto-load both globally via nix-ai, so this file deliberately does not re-import them — doing so would load every byte twice in each session. Non-Nix contributors…
multi-agent-ralph-loop CLAUDE.md
Claude Code instructions for alfredolopez80/multi-agent-ralph-loop, covering multi-agent ralph v3.0.0, analysis methodology, configuration location, browser automation (v3.0) and security hooks.