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/pilotspace/pilot-space/devgit clone --depth 1 https://github.com/pilotspace/pilot-spaceWhat 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 | $0.00012 | $0.01258 |
| Opus 5 | $0.00006 | $0.00629 |
| Sonnet 5 | $0.00002 | $0.00252 |
| Haiku 4.5 | $0.00001 | $0.00126 |
Grade A, and why
dev 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
User Request
$ARGUMENTS
Execution Flow
Parse → Discover → [Clarify?] → Load Patterns → Plan → Execute → Validate
Step 1: Parse Request
Extract from $ARGUMENTS:
| Field | Values |
|---|---|
| Type | feature | bugfix | refactor | test | docs |
| Target | service/module/file affected |
| Scope | specific files or "discover" |
| Flags | --ultrathink --expert --patterns --clarify |
Step 2: Codebase Discovery
For complex tasks or large codebase exploration (preferred):
Use Task tool with component-tracer agent to trace dependencies and understand components:
Task(subagent_type="component-tracer", prompt="Trace [component/service name] and its dependencies")
The component-tracer agent will provide:
- Component summary with responsibilities
- Full dependency tree (what it imports, what imports it)
- Related tests and configurations
- Integration points with other services
For simple/focused lookups:
Use mcp__serena tools directly:
mcp__serena__get_symbols_overview → File structure
mcp__serena__find_symbol → Locate classes/functions
mcp__serena__search_for_pattern → Find usage patterns
mcp__serena__find_referencing_symbols → Trace dependencies
Discovery strategy:
| Scenario | Approach |
|---|---|
| Unknown component structure | component-tracer agent |
| Cross-service dependencies | component-tracer agent |
| Specific symbol lookup | mcp__serena__find_symbol |
| Pattern search in known files | mcp__serena__search_for_pattern |
Report findings:
## Codebase Analysis
- **Related Files**: [discovered files]
- **Existing Patterns**: [similar implementations]
- **Dependencies**: [imports/services needed]
- **Integration Points**: [how component connects to others]
Step 3: Clarify (If Needed)
Clarify when ANY apply:
- Scope boundaries unclear
- Multiple valid approaches exist
- Breaking changes possible
- Security implications unclear
- Missing technical details
--clarifyflag provided
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 · 215 lines · 12 tokens per session scan A d5d9fd9a95c9
dev is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,258 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.