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/carolanelfbv/ios-development-agents/example-commandgit clone --depth 1 https://github.com/CarolaneLFBV/ios-development-agentsWhat 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 | $0.00011 | $0.00536 |
| Opus 5 | $0.00005 | $0.00268 |
| Sonnet 5 | $0.00002 | $0.00107 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
example-command 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/example-plugin:example-command - Template
Orchestrate a task described by $ARGUMENTS, coordinating specialists through phases.
This is a template. It uses the real Claude Code command format:
- Frontmatter: only
allowed-tools,description,argument-hint,modelare read by the harness.- Arguments arrive as
$ARGUMENTS(full string) or$1,$2… (positional). There is no{{var}}templating.- To delegate,
Taskmust be listed inallowed-tools, then spawn a subagent with the Task tool.
Arguments
| Flag | Values | Default | Description |
|---|---|---|---|
--complexity |
simple|medium|complex | medium | Depth of analysis and implementation |
--no-tests |
- | - | Skip the testing phase |
Delegation
Coordinate specialists via the Task tool. Run independent phases in parallel; sequence phases that depend on prior output.
- Analysis → spawn example-agent to break down the task, propose an approach, and flag risks.
- Implementation → spawn example-agent with the analysis to produce the code and docs.
- Testing → unless
--no-tests, spawn example-agent to write tests for the implementation.
Pass context between phases by including the previous phase's result text in the next Task prompt.
Workflow
1. analysis:
- Parse the task from $ARGUMENTS
- Delegate breakdown + plan + risks to example-agent
2. implementation:
- Delegate code + documentation, grounded in the analysis
3. testing: # skipped with --no-tests
- Delegate unit tests + fixtures for the implementation
Examples
/example-plugin:example-command "Create a caching helper" --complexity simple --no-tests
/example-plugin:example-command "Implement an offline sync engine" --complexity complex
Output
# Result: [Task]
## Analysis: Breakdown | Approach | Risks
## Implementation: Files created | Key decisions
## Tests: Coverage | Passing (unless --no-tests)
## Next Steps: Integration and verification
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 · 61 lines · 11 tokens per session scan A 0eb1ff66bb37
example-command is a command published in the GitHub repository CarolaneLFBV/ios-development-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 536 once invoked, about $0.0001 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 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.