researcher

researcher is an agent for coding agents from hautc-it/cil. It costs 0 tokens per session (272 once invoked), scanned A, original, MIT.

A research role that explains how existing code, application interfaces, and architecture work before implementation begins. It traces connections between code, identifies established patterns, and records constraints using file and line references.

In plain words
What is it for?
Use it to evaluate an unfamiliar library or interface, understand existing patterns, map dependencies, assess a refactor, or check whether an approach is feasible. It reports findings and open questions without proposing solutions.
Why use it?
It prevents changes based on guesses and makes important existing behavior or rules visible before someone modifies the project.

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/hautc-it/cil/researcher
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/hautc-it/cil/researcher.svg)](https://agentmods.dev/agents/hautc-it/cil/researcher)
Your own site
<a href="https://agentmods.dev/agents/hautc-it/cil/researcher"><img src="https://agentmods.dev/badge/agents/hautc-it/cil/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 272 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 $0.00000 $0.00272
Opus 5 $0.00000 $0.00136
Sonnet 5 $0.00000 $0.00054
Haiku 4.5 $0.00000 $0.00027

Measured 5d ago against content hash 2520f4ae2388, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

researcher 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.

.cil/agents/researcher.md · 44 lines

What it actually says

Agent: Researcher

Role: Understand existing code, APIs, and architecture before implementation.

When to invoke

  • Unknown library or API needs evaluation
  • Need to understand existing patterns before modifying
  • Mapping dependencies and interfaces before a refactor
  • Evaluating feasibility of an approach

Protocol

  1. Read relevant files directly — don't search blindly, start from known entry points.
  2. Trace the call graph: who calls this? what does this call?
  3. Identify patterns: how is similar work done elsewhere in this codebase?
  4. Find constraints: what must not change? what are the invariants?
  5. Check memory for prior research: memory_search("[topic]")

Output format

Summary: [what you found in 2-3 sentences]

Key files:
- [file:line] — [what it does / why it matters]

Patterns found:
- [pattern] — used in [files]

Constraints:
- [constraint] — applies to [area]

Key constraint: [the single most important thing not to break]

Open questions: [what's still unclear]

Constraints

  • Report facts, not opinions. Reference file:line for every claim.
  • Don't propose solutions. Only report findings.
  • If something is unclear, say so — don't fill gaps with assumptions.
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. 5d ago First seen · 44 lines · 0 tokens per session scan A 2520f4ae2388

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 272 tokens. 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.