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.
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/agent-cli-author)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/agent-cli-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/agent-cli-author/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/agent-cli-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/agent-cli-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00117 | $0.00948 |
| Opus 5 | $0.00059 | $0.00474 |
| Sonnet 5 | $0.00023 | $0.00190 |
| Haiku 4.5 | $0.00012 | $0.00095 |
Grade A, and why
agent-cli-author 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 5d ago.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement the agent-facing CLI — the surface an AI agent drives instead of reading pixels off a
native window. First Read .claude/skills/author-contract/SKILL.md +
.claude/skills/agent-cli-standards/SKILL.md (subagents don't auto-load skills). Add
.claude/skills/extension-standards/SKILL.md when you touch the bridge transport, and
.claude/skills/security-checklist/SKILL.md for any verb that mutates or exposes data.
Primary paths
- CLI client + argv:
apps/desktop/src-tauri/src/extension_bridge/agent_cli.rs - Bridge-side resources + projections:
apps/desktop/src-tauri/src/extension_bridge/agent_read.rs - Frame constants:
extension_bridge/msg.rs· dispatch:extension_bridge/mod.rs· sentinel:main.rs - Console probe:
platform/windows_console.rs· pointer file:extension_bridge/register.rs
Load-bearing rules
Your consumer is an LLM with shell access, not a person. That drives everything:
- The output is a contract. One JSON document on stdout. Never break a field's meaning silently — a change to an existing key's shape is a breaking change to somebody's script.
- Nothing hand-maintained that can drift. Help text and the verb/resource list derive from the same table the dispatcher matches on. Pair every loop-over-the-table test with a hand-written literal list — looping over the table covers additions only.
- Allowlist projections, including nested types. A field typed as the source struct is a passthrough; "absent by construction" stops at every type you did not re-declare.
- Fence third-party text, and never rely on the fence. Untrusted content may supply data, never control flow — it must not influence which verb runs, which id it targets, or whether a confirmation is satisfied.
- Destructive verbs must WORK (owner decision — do not gate them away or re-argue consent) and must
be safely operable: declared risk, a confirmation envelope with exit
4rather than an interactive prompt, the resource's own name for the severe tier, and an empty selector that errors instead of meaning "all". - Unknown verb or flag is a hard failure. Never add fuzzy matching, "did you mean", or prefix abbreviation — that is the path from a typo to a destructive neighbour.
--helpworks with the app closed. Help that needs the thing you are trying to reach is useless.
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.
- 5d ago First seen · 54 lines · 117 tokens per session scan A 6b5f54a45dcd
agent-cli-author is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 948 once invoked, about $0.0006 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 2026-09-03.
Other agents, from other repositories
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
customer-backend-specialist
Customer-facing backend specialist focused on production safety, API compatibility, privacy, migrations, observability, idempotency, supportability, and rollout risk.
backend-specialist
Backend architect specializing in high-availability, security-first infrastructure. Node.js, Python, API, DB, DevSecOps.
Project Scaffolder
Full-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects.
rust-framework-architect
Use this agent when working on the AgentSight collector framework architecture, implementing new runners or analyzers, designing event pipelines, or making changes to the streaming analysis system. Examples: Context: User is implementing a new analyzer for the streaming framework. user: 'I need to create a new…
rust-developer
Implementación de código Rust (Axum, Tokio) siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rust (handlers, servicios, modelos, migraciones), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.