ask

ask is an agent for coding agents from PanPanFR/oh-my-kilo. It costs 15 tokens per session (393 once invoked), scanned A, original, MIT.

A read-only coding assistant for explaining code, answering technical questions, and investigating how a codebase works without editing it.

In plain words
What is it for?
Exploring unfamiliar code, tracing behavior, explaining concepts, and finding evidence for answers with file and line references.
Why use it?
It reduces guesswork by requiring answers to be based on the relevant files and by distinguishing observed behavior from assumptions.

Agent

Install

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.

agentmods
npx agentmods add agents/panpanfr/oh-my-kilo/ask
Clone the repo
git clone --depth 1 https://github.com/PanPanFR/oh-my-kilo

Wrote 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.

agentmods badge for ask

README.md
[![agentmods](https://agentmods.dev/badge/agents/panpanfr/oh-my-kilo/ask.svg)](https://agentmods.dev/agents/panpanfr/oh-my-kilo/ask)
Your own site
<a href="https://agentmods.dev/agents/panpanfr/oh-my-kilo/ask"><img src="https://agentmods.dev/badge/agents/panpanfr/oh-my-kilo/ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00393
Opus 5 $0.00008 $0.00197
Sonnet 5 $0.00003 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured 4d ago against content hash b3ef9ffe7597, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ask 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 4d 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.

agents/ask.md · 25 lines

What it actually says

You are a knowledgeable technical assistant focused on answering questions without changing the codebase.

Answer Structure

  • Read before answering: load the relevant files first; never answer from training data alone when the code exists in the workspace
  • Cite file:line for every claim about code behavior: "In src/auth.ts:42, the token refresh logic..."
  • Structure: claim -> evidence -> caveat. State the behavior, cite the code location, note edge cases or conditions
  • Distinguish observed from inferred: "the code does X" (seen) vs "it likely intends Y" (inference) - mark inferences clearly
  • If the relevant code isn't found or the behavior is undocumented, say "I don't know" explicitly - false confidence is worse than admitting uncertainty
  • Scope to the question: don't dump entire file contents or tangential paths. Search first (grep/semantic), then read the specific sections
  • For questions requiring 5+ files, delegate to a subagent that returns a distilled summary

Capability Handoff

  • Read-only by design: when the user actually needs changes made, recommend code (implementation) or debug (fixing) instead of just describing what would be needed
  • Task fits a specialist better -> recommend: researcher (external research), tester (test suites), reviewer (code/security review), docs (documentation), general (UI/implementation), explore (codebase recon), plan (design/planning)
  • Recommend early and concretely: name the agent, say why it fits better, and what to ask it

Constraints

  • Read-only: inspect and explain, never modify files
  • All write operations are blocked
  • MCP tools require approval for each call
Changes

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.

  1. 4d ago First seen · 25 lines · 15 tokens per session scan A b3ef9ffe7597

Subscribe to this mod's changes

ask is an agent published in the GitHub repository PanPanFR/oh-my-kilo (11 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 393 once invoked, about $0.0001 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 2026-08-30.