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/jnarowski/agentcmd/refresh-docsgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00008 | $0.02628 |
| Opus 5 | $0.00004 | $0.01314 |
| Sonnet 5 | $0.00002 | $0.00526 |
| Haiku 4.5 | $0.00001 | $0.00263 |
Grade A, and why
refresh-docs 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 today.
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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Documentation
Regenerate AgentCmd documentation by extracting current state from codebase sources of truth. Updates AUTO-GENERATED sections while preserving hand-crafted content.
Variables
$section: $1 (optional) - Specific section to refresh or 'all' (default: all)- Valid sections:
step-types,sdk-api,slash-commands,cli,config,examples,all
Documentation Decisions
These decisions guide all documentation generation:
- Audience: Intermediate (familiar with AI CLI tools like Claude Code, Cursor)
- Format: Section-appropriate
- Concepts/philosophy pages: Mermaid diagrams, visual explanations
- Reference/API pages: Code-heavy with minimal prose
- Examples: Tiered complexity
- Getting Started: Ultra-simple (5-10 lines, single concept)
- Step Types Reference: Focused snippets (isolated examples)
- Examples & Recipes: Real workflows (from
.agent/workflows/definitions/example-*.ts) - Advanced Topics: Production patterns with full context
- Tone: Technical & concise but fun
- Structure: Follow Fumadocs conventions (meta.json, frontmatter)
- Update Strategy: Generated docs serve as templates for future runs
Workflow
- Extract context from 6 sources (load current codebase state)
- Read existing docs (use as templates)
- Generate updated content (surgical updates to AUTO-GENERATED sections)
- Validate comprehensively (links, syntax, signatures)
- Write updated files (no auto-commit)
- Report (changed files, warnings)
Sources of Truth
Load context from these 6 sources to inform documentation generation:
1. TypeScript Types
Source: packages/agentcmd-workflows/src/types/steps.ts
Generates: Step Types Reference (all 8 step configs with signatures, timeouts)
Extraction: Read file, extract interface definitions for:
AgentStepConfig,AiStepConfig,CliStepConfig,GitStepConfigArtifactStepConfig,AnnotationStepConfig,PhaseOptions- Note timeout constants in comments
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.
- today First seen · 371 lines · 8 tokens per session scan A ba852b7f205c
refresh-docs is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 2,628 once invoked, about $0.0000 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 2026-09-01.
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.