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/sakrut/ai-code-graph/command-pipelinegit clone --depth 1 https://github.com/sakrut/ai-code-graphWhat 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 | $0.00000 | $0.00407 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
command-pipeline 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 yesterday.
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
97% identical to command-pipeline — 13 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.
What it actually says
Command Pipeline
Arguments: $ARGUMENTS Execute a pipeline of commands based on a specification.
Arguments: $ARGUMENTS
Command Pipeline Execution
Parse pipeline specification from arguments. Supported formats:
Simple Pipeline
init → expand-all → sprint-plan
Conditional Pipeline
status → if:pending>10 → sprint-plan → else → next
Iterative Pipeline
for:pending-tasks → expand → complexity-check
Smart Pipeline Patterns
1. Project Setup Pipeline
init [prd] →
expand-all →
complexity-report →
sprint-plan →
show first-sprint
2. Daily Work Pipeline
standup →
if:in-progress → continue →
else → next → start
3. Task Completion Pipeline
complete [id] →
git-commit →
if:blocked-tasks-freed → show-freed →
next
4. Quality Check Pipeline
list in-progress →
for:each → check-idle-time →
if:idle>1day → prompt-update
Pipeline Features
Variables
- Store results:
status → $count=pending-count - Use in conditions:
if:$count>10 - Pass between commands:
expand $high-priority-tasks
Error Handling
- On failure:
try:complete → catch:show-blockers - Skip on error:
optional:test-run - Retry logic:
retry:3:commit
Parallel Execution
- Parallel branches:
[analyze | test | lint] - Join results:
parallel → join:report
Execution Flow
- Parse pipeline specification
- Validate command sequence
- Execute with state passing
- Handle conditions and loops
- Aggregate results
- Show summary
This enables complex workflows like:
parse-prd → expand-all → filter:complex>70 → assign:senior → sprint-plan:weighted
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.
- yesterday First seen · 80 lines · 0 tokens per session scan A 9b899bcc4c80
command-pipeline is a command published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. A static security scan graded it A with 0 findings. It is 97% identical to command-pipeline, differing in 13 lines, and is treated as a copy.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.