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/janumansky/startup/firegit clone --depth 1 https://github.com/JanUmansky/startupWhat 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 | $0.00475 |
| Opus 5 | $0.00000 | $0.00237 |
| Sonnet 5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
fire 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.
What it actually says
/fire — Remove an existing assistant command
Definitions:
- COMMANDS_DIR = the folder where command markdown files live.
- ROSTER_FILE = COMMANDS_DIR + "/_roster.md"
- Command file path = COMMANDS_DIR + "/.md"
Goal: Remove an assistant command file and unregister it from ROSTER_FILE.
Input
User message: "/fire " (e.g., "/fire bob" or "/fire api-guardian")
Reserved Names (Protected)
The following names are system commands and cannot be fired:
- hire, fire, update, list, define, _roster
If the user attempts to fire a reserved name, reject the request with a clear error:
❌ Cannot fire
<name>— this is a protected system command. Only hired assistants can be removed with /fire.
Steps
- Extract assistant name.
- Validate the name is not reserved:
- Check against reserved names: hire, fire, update, list, define, _roster
- If reserved, reject immediately with the error message above
- Do NOT proceed with deletion
- Resolve the command file:
- Prefer exact match COMMANDS_DIR/.md
- If not found, search within ROSTER_FILE for close matches and select the best candidate.
- Delete the assistant command file.
- Update ROSTER_FILE:
- Remove the assistant's entry under "Active Assistants".
- Report what was removed with structured output.
Output Format
Structure the response with emojis and tables:
🔥 Summary
One sentence: who was fired.
Example: Removed dinesh from your team.
📁 Changes
| Action | File | Location |
|---|---|---|
| 🗑️ Deleted | dinesh.md |
.cursor/commands/ |
| 📝 Updated | _roster.md |
.cursor/commands/ |
👥 Remaining Team
| Agent | Mission |
|---|---|
🔧 /gilfoyle |
DevOps Specialist |
Use /list to see full team details.
Safety
- Only delete within COMMANDS_DIR unless explicitly asked.
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 · 71 lines · 0 tokens per session scan A c90a4c2dcb51
fire is a command published in the GitHub repository JanUmansky/startup (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 475 tokens. 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.