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/generate-bug-specgit 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 | $0.00009 | $0.02777 |
| Opus 5 | $0.00005 | $0.01388 |
| Sonnet 5 | $0.00002 | $0.00555 |
| Haiku 4.5 | $0.00001 | $0.00278 |
Grade C, and why
generate-bug-spec scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore-start --> How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix Specification
Generate focused spec for bugs with reproduce → diagnose → fix → verify workflow. Creates spec at .agent/specs/todo/[id]-[bug]/spec.md with timestamp-based ID.
Variables
- $param1: $1 (optional) - Bug context or description (infers from conversation if omitted)
Instructions
- IMPORTANT: Use reasoning model - THINK HARD about reproduction, root cause, AND fix approach
- IMPORTANT: This command ONLY generates spec - do NOT implement code or make changes beyond spec folder/file and index.json
- Your ONLY file operations: create spec folder, write spec.md, update index.json - nothing else
- Normalize bug name to kebab-case for folder name
- Replace ALL
<placeholders>with specific details - Formalize reproduction steps - make them precise and repeatable
- Root Cause is iterative - start with hypothesis, update during investigation
- Create detailed tasks with specific file paths and commands
- Assign complexity (1-10) to EVERY task
- Order tasks by dependencies
- DO NOT include hour estimates - use complexity points only
Complexity Scale
Assign based on context window usage and cognitive load:
- 1-2/10: Trivial - Single file, <50 lines, minimal context
- 3-4/10: Simple - Few files, straightforward logic
- 5-6/10: Moderate - Multiple related files, moderate context
- 7-8/10: Complex - Cross-cutting change, high context
- 9-10/10: Very complex - Architectural change, deep knowledge required
Key principle: Higher complexity = more context agent needs to load/understand
Workflow
-
Determine Context:
- If $param1 provided: Use as context
- If $param1 empty: Infer from conversation history
-
Generate Spec ID:
- Generate timestamp-based ID in format
YYMMDDHHmmusing current local time - Example: November 13, 2025 at 2:22pm local →
2511131422 - Read
.agent/specs/index.json(will be updated in step 8)
- Generate timestamp-based ID in format
-
Generate Bug Name:
- Generate concise kebab-case name from context (max 4 words)
- Examples: "Memory leak in workflows" → "workflow-memory-leak", "Export crash" → "export-crash-fix"
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 · 364 lines · 9 tokens per session scan C 7ef633e5b895
generate-bug-spec is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 9 tokens to every session and 2,777 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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.