Borrowing it
Nothing to install: this file belongs to realEbi/askCode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/realEbi/askCode/main/.claude/skills/add-agent/SKILL.mdgit clone --depth 1 https://github.com/realEbi/askCodeWrote 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/skills/realebi/askcode/add-agent)<a href="https://agentmods.dev/skills/realebi/askcode/add-agent"><img src="https://agentmods.dev/badge/skills/realebi/askcode/add-agent/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/skills/realebi/askcode/add-agent"><img src="https://agentmods.dev/badge/skills/realebi/askcode/add-agent.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 | $0.00064 | $0.00646 |
| Opus 5.5 | $0.00026 | $0.00258 |
| Sonnet 5.5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
add-agent 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 2mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task: Add a New Agent to askCode.nvim
You are implementing a new agent named $agent_name whose CLI is invoked as:
$cli_invocation
Follow the implementation plan in .agents/add-new-agent.md exactly. The relevant source files are:
lua/askCode/agents/— existing agents to use as referencelua/askCode/agents/init.lua— agent registry (must be updated).agents/summary/interfaces.md— config schema docs (must be updated)tests/— existing test files to use as reference
Current agent registry
cat lua/askCode/agents/init.lua
Execution steps
Work through these steps in order. Do not skip any.
Step 1 — Analyse the CLI output format.
Determine whether $cli_invocation produces plain text, a single JSON object, or a JSON event stream. Use that to select the correct parse_response strategy from the plan.
Step 2 — Determine the prompt input method.
If the CLI reads the prompt from a flag argument (e.g. -p "...") or if prompts can contain code with newlines, use the tempfile method. If the CLI reads from stdin, use the shellescape+pipe method.
Step 3 — Create lua/askCode/agents/$agent_name.lua.
Implement all four exports: setup, prepare_command, parse_response, ask. Use the chosen strategies from Steps 1 and 2.
Step 4 — Register the agent.
Add $agent_name = require("askCode.agents.$agent_name") to the M.agents table in lua/askCode/agents/init.lua.
Step 5 — Update documentation.
In .agents/summary/interfaces.md, append | "$agent_name" to the agent config comment line.
Step 6 — Write unit tests.
Create tests/test_$agent_name_agent.lua with all four test groups: setup, prepare_command, parse_response, ask. Mock io.popen in all ask tests. The mock output for the success case must be a string that the real CLI would produce, and the expected parsed value must match what parse_response returns for that input.
Step 7 — Verify.
Run make test and confirm the output shows Fails (0) and all cases for test_$agent_name_agent.lua are green. If any test fails, fix the implementation before finishing.
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.
- 2mo ago First seen · 53 lines · 64 tokens per session scan A e917ebb20523
add-agent is a skill published in the GitHub repository realEbi/askCode (4 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 646 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
add-agent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-agentrealEbi/askCode | Skill | 4 | 6mo ago | MIT | A | 64 | Claude Code |
| skillgrade-gradersmgechev/skillgrade | Skill | 735 | 26d ago | MIT | A | 63 | Claude Code, Codex |
| angular-modern-apismgechev/skillgrade | Skill | 735 | 26d ago | MIT | A | 20 | Claude Code, Codex |
| superlintmgechev/skillgrade | Skill | 735 | 26d ago | MIT | A | 0 | Claude Code, Codex |
| skillgrade-setupmgechev/skillgrade | Skill | 735 | 26d ago | MIT | A | 58 | Claude Code, Codex |
| ainb-fleet:daemonsstevengonsalvez/agents-in-a-box | Skill | 27 | 7d ago | MIT | A | 126 | Claude Code |
| ainb-fleet:bridgestevengonsalvez/agents-in-a-box | Skill | 27 | 7d ago | MIT | A | 147 | Claude Code |