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/davidmatousek/agentic-oriented-development-kit/aod.rungit clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kitWhat 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 | $0.00040 | $0.01457 |
| Opus 5 | $0.00020 | $0.00728 |
| Sonnet 5 | $0.00008 | $0.00291 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
aod.run 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 2d 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.
This is a copy
100% identical to aod.run — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Overview
Single-command lifecycle orchestrator. Accepts 4 input modes and 1 combinable flag (--dry-run), and delegates to the ~aod-run skill.
Usage: /aod.run <idea | #NNN | --resume | --status | --dry-run>
Entry Points:
| Command | Mode | What It Does |
|---|---|---|
/aod.run "Add dark mode toggle" |
New idea | Starts full lifecycle at Discover stage |
/aod.run #22 or /aod.run 22 |
Issue | Reads GitHub Issue, resumes from current stage |
/aod.run --resume |
Resume | Continues from last state checkpoint on disk |
/aod.run --status |
Status | Read-only display of current orchestration state |
/aod.run --status #22 |
Status | Inferred status for a specific issue (no state file needed) |
/aod.run --dry-run "Add dark mode" |
Dry-run | Preview full lifecycle without executing |
/aod.run --dry-run #22 |
Dry-run | Preview from issue without executing |
/aod.run --dry-run --resume |
Dry-run | Preview resume without executing |
State File: .aod/run-state.json — persisted after every stage transition for session resilience.
Skill Reference: .claude/skills/~aod-run/SKILL.md — full orchestration logic.
Step 0: Parse Flags
Parse optional flags from $ARGUMENTS. Flags must appear at the start of arguments.
Step 0a: Parse --dry-run
Check if $ARGUMENTS starts with --dry-run:
-
If
$ARGUMENTSstarts with--dry-run:- Set
dry_run = true - Strip
--dry-runfrom the beginning of$ARGUMENTS(trim leading whitespace from remainder) - Continue to Step 1 with the remaining arguments
- Set
-
If
$ARGUMENTSdoes NOT start with--dry-run:- Set
dry_run = false - Continue to Step 1 with
$ARGUMENTSunchanged
- Set
Step 1: Parse Input Mode
Read the (possibly stripped) arguments and determine the entry mode:
- Status mode: Arguments start with
--status- If followed by
#NNNorNNN: set mode =status, issue = NNN - If no number: set mode =
status, issue = null
- If followed by
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.
- 2d ago First seen · 140 lines · 40 tokens per session scan A 4275d5a07e3a
aod.run is a command published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,457 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aod.run, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.