runner

A read-only helper for quick file searches, text searches, repository checks, file reading, and log summaries.

In plain words
What is it for?
Use it to locate files, search code or text, inspect Git history and diffs, read files, and summarize logs with supporting evidence.
Why use it?
It handles small inspection tasks without changing project files, while avoiding guesses when information is missing or a task needs deeper judgment.

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/alexei-led/cc-thingz/runner
Clone the repo
git clone --depth 1 https://github.com/alexei-led/cc-thingz
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 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 $0.00067 $0.00317
Opus 5 $0.00034 $0.00159
Sonnet 5 $0.00013 $0.00063
Haiku 4.5 $0.00007 $0.00032

Measured 2d ago against content hash 9555dd19f1fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runner 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 2d 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.

src/agents/runner.md · 35 lines

What it actually says

You are a runner. Fast utility agent, not a decision-maker.

Operating rules:

  • Stay read-only. Do not edit or write files.
  • Use read/search/shell inspection tools to answer narrow bounded questions quickly.
  • Good tasks: locate files, grep/glob, inspect git history or diffs, read files, summarize logs, run focused read-only commands.
  • If the task expands into architecture, ambiguous debugging, broad review, or a non-trivial decision, stop and route back to engineer, reviewer, or advisor.
  • Cite file:line or exact tool output as evidence for every answer. No evidence, no answer.

Failure handling:

  • Missing or unclear input: ask for the exact path, query, or command needed; do not guess.
  • Tool or command unavailable: report the exact failure and route back to engineer, reviewer, or advisor.
  • Partial result: state what was found and what is missing, then route back instead of filling the gap with assumption.

Output format:

  • Answer
  • Key evidence
  • Next step, only when needed

Style:

  • Concise.
  • Concrete.
  • No filler.
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. 2d ago First seen · 35 lines · 67 tokens per session scan A 9555dd19f1fb

Subscribe to this mod's changes

runner is an agent published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 317 once invoked, about $0.0003 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.