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 commands/iamironz/ai-config-bundle/indexgit clone --depth 1 https://github.com/iamironz/ai-config-bundleWrote 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/commands/iamironz/ai-config-bundle/index)<a href="https://agentmods.dev/commands/iamironz/ai-config-bundle/index"><img src="https://agentmods.dev/badge/commands/iamironz/ai-config-bundle/index.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 | $0.00000 | $0.00698 |
| Opus 5 | $0.00000 | $0.00349 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
INDEX 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands Index
Canonical command playbooks live under ai-kb/commands/.
Tool-specific command files (Cursor/OpenCode) should be thin wrappers that delegate here.
Shared Conventions
- Command input is the text after the command name; treat it as the request and constraints for the invocation.
- Follow
ai-kb/AGENTS.mdfor the operational loop and<rule_context>citation protocol. - For command offloading/parallelization policy:
ai-kb/rules/command-orchestration.md. - Parallel background subagents are the default execution mode across commands unless the user explicitly requests sequential/main-thread execution.
- Background-first is mandatory for implementation, analysis, and research work; keep main-thread work to orchestration and synthesis.
- For non-trivial natural-language requests, load
command-parity-routerskill first and infer command-intent automatically. - If
command-parity-routercannot be loaded, applyai-kb/rules/skill-routing.mddirectly. - When runtime state, plugin hooks, internal sessions, or nested delegation are in scope, also load
ai-kb/rules/plugin-safety.mdandai-kb/rules/delegation-depth.md. - For KB recommendation workflow:
ai-kb/rules/kb-maintenance.md.
Command Catalog
| Command | Canonical doc | Use for |
|---|---|---|
create_plan |
ai-kb/commands/create_plan.md |
Explore options and draft a plan in the same response (iterate with feedback) |
execute_plan |
ai-kb/commands/execute_plan.md |
Execute an existing plan without editing it |
implement_feature |
ai-kb/commands/implement_feature.md |
Implement a new feature (TDD-first when feasible) |
fix_issue |
ai-kb/commands/fix_issue.md |
Diagnose and fix a bug (TDD-first when feasible) |
implement_tests |
ai-kb/commands/implement_tests.md |
Add missing tests and run them immediately |
run_tests |
ai-kb/commands/run_tests.md |
Run the most relevant test scope for changes |
run_build |
ai-kb/commands/run_build.md |
Run the most relevant build step for changes |
review_code |
ai-kb/commands/review_code.md |
Review code for quality, architecture, risks |
validate_domain |
ai-kb/commands/validate_domain.md |
Verify behavior matches domain/spec requirements |
validate_runtime |
ai-kb/commands/validate_runtime.md |
Debug runtime behavior, logs, state timelines |
research |
ai-kb/commands/research.md |
Research uncertain APIs/errors/best practices |
update_docs |
ai-kb/commands/update_docs.md |
Update project docs to match changes |
update_rule |
ai-kb/commands/update_rule.md |
Add/update/compact KB rules and structure |
suggest_kb_updates |
ai-kb/commands/suggest_kb_updates.md |
Propose KB updates from durable learnings |
commit |
ai-kb/commands/commit.md |
Create local git commits (opt-in, approval gated) |
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 · 37 lines · 0 tokens per session scan A 49f3d28ee62a
INDEX is a command published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 698 tokens. 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 commands, from other repositories
ink-art
Hand-drawn ink-on-white doodle animation — a character that draws itself then walks/dances/waves, or a deadpan contraption explainer. Vector, deterministic, rendered via HyperFrames to MP4.
animated-drawing
Animate a SUPPLIED drawing/photo of a character with real motion capture (Meta AnimatedDrawings) → raster GIF/MP4 of that drawing moving. To CREATE a vector doodle from scratch, use /ink-art.
backlot
Open the Backlot living storyboard — the browser board that shows pipeline stages, script, scene plan, and generated assets live as a production runs.
README
Codex only scans /.codex/prompts/ (user home) for custom prompts — it does not read project-level .codex/prompts/. These files are versioned here as the source of truth; to use them in Codex, copy or symlink them into your home dir.
fastapi_stripe
A Stripe Checkout implementation takes four steps.
standalone-python-scripts
Command "standalone-python-scripts" from iloveitaly/llm-ide-rules, covering standalone python scripts, /// script, requires-python = ">=3.13", dependencies = [] and ///.