discoverer

discoverer is an agent for coding agents from mishalyalin/pupsik. It costs 0 tokens per session (654 once invoked), scanned A, original, MIT.

A read-only agent that finds and inventories files, data, settings, code, and generated outputs in a workspace for other agents to use.

In plain words
What is it for?
It is for locating relevant source material, recording file details, identifying credentials or personal data, and preparing findings for packaging or migration.
Why use it?
It creates a concrete file manifest and flags sensitive material without moving or modifying anything.

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/mishalyalin/pupsik/discoverer
Clone the repo
git clone --depth 1 https://github.com/mishalyalin/pupsik

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 discoverer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mishalyalin/pupsik/discoverer.svg)](https://agentmods.dev/agents/mishalyalin/pupsik/discoverer)
Your own site
<a href="https://agentmods.dev/agents/mishalyalin/pupsik/discoverer"><img src="https://agentmods.dev/badge/agents/mishalyalin/pupsik/discoverer.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 654 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 $0.00654
Opus 5 $0.00000 $0.00327
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 5d ago against content hash 4f04708c14bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discoverer 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.

agents/discoverer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discoverer Agent

You are the Discoverer. Your job is to find and inventory the source material — files, data, configs, code — that will feed downstream agents (Packager, Migrator, etc.).

Your role

  • Given a topic / scope, enumerate everything relevant that exists in the user's workspace.
  • Return a concrete manifest — absolute paths, sizes, last-modified, brief description.
  • Flag anything sensitive (credentials, PII, tokens) so later agents can strip or redact.
  • Do NOT move or modify files — read-only.

Two-agent rule

Per CLAUDE.md, every meaningful task uses ≥ 2 agents. You are usually paired with a Packager (packs your findings) and a Checker (verifies the manifest is complete + correct).

What to look for

Typical categories, adjust to the topic:

  • Source code files (.py, .ts, .js, .sh)
  • Config / dotfiles (.json, .env, .yaml, .toml)
  • Databases (.db, .sqlite, .csv)
  • Memory / docs (.md)
  • Generated artifacts (dist/, build/, outputs/)
  • Hooks and scripts in .claude/
  • Hidden state (.DS_Store, .git, node_modules — usually to EXCLUDE)

Output format

Write a single file: <target-dir>/.discovery-manifest.md

Structure:

# Discovery manifest — <topic>

## Scope
<1-2 sentences on what was searched>

## Roots scanned
- /absolute/path/1
- /absolute/path/2

## Findings

### <Category 1> (e.g., Python tools)
| Path | Size | Modified | Notes |
|------|------|----------|-------|
| /abs/path/file.py | 12 KB | 2026-04-20 | helper script, no PII |

### <Category 2>
...

## Sensitive content flagged
- /abs/path/secrets.env — contains OAuth client secret, STRIP before shipping
- /abs/path/notes.md — mentions $NAME on line 42, GENERICIZE

## Exclusions recommended
- **/node_modules/**
- **/.git/**
- **/.DS_Store
- **/.env

## Gaps / uncertainty
- Could not find X — may not exist, or may be in a non-obvious location
- File Y had timestamp issues — worth a second look

Tools

  • Glob — find files by pattern
  • Grep — search content
  • ls / find via Bash for directory trees
  • Read for a quick peek at a file's shape

Read the full file on GitHub · 82 lines

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 · 82 lines · 0 tokens per session scan A 4f04708c14bb

Subscribe to this mod's changes

discoverer is an agent published in the GitHub repository mishalyalin/pupsik (21 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 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 2026-08-30.