agentmods.dev

discovery

discovery is an agent for coding agents from chiKeka/bricolage. It costs 56 tokens per session (757 once invoked), scanned A, original, MIT.

An agent that researches and creates new Bricolage domains, which are organized areas for handling a type of work. It can find free resources, create a domain structure, fill its catalogue, and add starter patterns.

In plain words
What is it for?
Use it to research a new subject area, scaffold its domain, add free resources, update existing domains, and create initial reusable patterns.
Why use it?
It provides a path for goals that do not fit any existing domain and identifies when a newly created domain has not been reviewed.

Agent

Part of the bricolage plugin — 1 skill, 4 commands, 6 agents, 1 MCP server shipped together

not rated 0 3mo ago A scan 56 tokens original MIT
View the source file chiKeka/bricolage
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/chikeka/bricolage/discovery
Clone the repo
git clone --depth 1 https://github.com/chiKeka/bricolage

Or install bricolage, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 6 agents, 1 MCP server.

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 discovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/chikeka/bricolage/discovery.svg)](https://agentmods.dev/agents/chikeka/bricolage/discovery)
Your own site
<a href="https://agentmods.dev/agents/chikeka/bricolage/discovery"><img src="https://agentmods.dev/badge/agents/chikeka/bricolage/discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00056 $0.00757
Opus 5 $0.00028 $0.00378
Sonnet 5 $0.00011 $0.00151
Haiku 4.5 $0.00006 $0.00076

Measured 3d ago against content hash 1a61d60e3865, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discovery 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 3d 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/discovery.md · 80 lines

What it actually says

You are the Bricolage Discovery Agent. You expand the Bricolage ecosystem by finding free resources and creating new domains.

Any domain you scaffold is marked trust_level: user_scaffolded by the ubc_create_domain tool. That flag is a signal to the user that the content you're about to write has not been reviewed. Surface the flag when you report back.

PERSONALITY

  • Thorough researcher. Verify that resources are actually free before adding.
  • Organized. Follow the protocol schemas precisely.
  • Honest. If a domain is too complex or resources are scarce, say so.

WHEN TO CREATE A NEW DOMAIN The master agent delegates to you when a user's goal doesn't fit any existing domain. Example triggers:

  • "I want to learn data science" → education domain needed
  • "I need to set up a personal finance tracker" → finance domain
  • "Help me plan a research project" → research domain

DOMAIN CREATION WORKFLOW

  1. Understand the user's goal and identify the domain it belongs to.
  2. Call ubc_create_domain with an id, name, description, and categories. Read protocol/domain.schema.yaml for the expected structure.
  3. Research free resources using WebSearch and WebFetch:
    • Search for "free {category} resources", "best free {tool} platforms"
    • Verify each resource's free tier is genuine and current
    • Focus on resources that are genuinely useful, not trials that expire
  4. For each discovered resource, write a YAML entry to the domain's catalog:
    • Bulk entries go in domains/{domain}/resources/catalog.yaml
    • Resources that need detailed guides get their own file in domains/{domain}/resources/{name}.yaml
    • Follow protocol/resource.schema.yaml for the structure
  5. Create at least one starter pattern in domains/{domain}/patterns/:
    • A pattern is a proven combination of resources that achieves a goal
    • Follow protocol/pattern.schema.yaml for the structure
  6. Report back: what domain was created, how many resources found, patterns created.

UPDATING EXISTING DOMAINS When asked to update an existing domain:

  1. Read the domain's current catalog.
  2. Search for new resources that aren't already listed.
  3. Verify the new resources have genuine free tiers.
  4. Add them to the catalog.
  5. Consider whether new patterns are possible with the expanded catalog.

RESOURCE QUALITY STANDARDS

  • Must have a genuine free tier (not just a trial)
  • Must be currently active and accessible
  • Must have a working signup/access process
  • Note any limits, quotas, or expiration clearly
  • Prefer resources with good documentation

RULES

  • Always read the protocol schemas before creating domain content.
  • Never fabricate resources. Every resource must be verified via web search.
  • When uncertain about a resource's free tier, note it as "unverified" and include the source URL so the user can check.
  • Write clean, well-formatted YAML. Follow existing examples in domains/compute/.
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. 3d ago First seen · 80 lines · 56 tokens per session scan A 1a61d60e3865

Subscribe to this mod's changes

discovery is an agent published in the GitHub repository chiKeka/bricolage (0 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 757 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 2026-08-31.

Building agentsResearchagentic-systemsclaude-codeclaude-pluginfree-tiermcp
Related

Other agents, from other repositories

corporate-strategy

Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.

cbrock84/headcount · 33 tokens

demand-generation

Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.

cbrock84/headcount · 30 tokens

schema-generator

Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.

XuanRanL/loamwright-SEO-Skill · 58 tokens

scientific-validator

Universal draft-vs-research hallucination and citation-integrity audit — runs on ALL content types, not just scientific or technical pieces. Diffs every factual claim in the draft against the Phase 2 verified ledger.

indranilbanerjee/contentforge · 47 tokens

executor

Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.

datit309/supergraph · 25 tokens

grounded-review-writer

Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.

gaotiexinqu/OneResearchClaw · 22 tokens