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/hiregit 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 | $0.01180 |
| Opus 5 | $0.00000 | $0.00590 |
| Sonnet 5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
hire scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X GET http://localhost:3000/api/users How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hire — Create a new scoped code-writing assistant command
You are operating in a repository that supports “slash commands” backed by markdown files in a configurable commands folder.
Definitions:
- COMMANDS_DIR = the folder where command markdown files live (this file is already in it).
- ROSTER_FILE = COMMANDS_DIR + "/_roster.md"
- A “command” named X is stored as: COMMANDS_DIR + "/X.md"
Goal: Create a NEW assistant command file based on the user’s prompt, and register it in ROSTER_FILE.
Input (from the user)
The user message invoking /hire contains:
- desired assistant name (optional)
- role + scope description (required) Example: "/hire bob a backend developer focused on API routes scalability, standardization and security"
Reserved Names
The following names are system commands and cannot be used for hired assistants:
- hire, fire, update, list, define, _roster
If the user attempts to hire an assistant with a reserved name, reject the request with a clear error:
❌ Cannot hire an assistant named
<name>— this is a reserved system command. Please choose a different name.
Steps
-
Parse the user's /hire message and extract:
- Proposed name (if missing, invent a short, relevant name)
- Role
- Scope & focus areas
- Constraints / tech hints
-
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 file creation
-
Scan the codebase QUICKLY to infer conventions:
- Language(s), frameworks, folder structure
- API patterns (routing/controllers/middleware)
- Validation/auth patterns
- Error handling/logging style
- Testing approach
- Lint/format rules if visible DO NOT reference specific files unless explicitly instructed by the user
-
Decide final assistant command name:
- lowercase kebab-case
- avoid collisions (if exists, append -2, -3...)
- if user supplied a name, prefer it unless it conflicts badly
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 · 195 lines · 0 tokens per session scan A 31106b315e2c
hire 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 1,180 tokens. A static security scan graded it A with 1 finding (makes network calls). 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.