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.
npx agentmods add agents/chikeka/bricolage/mastergit clone --depth 1 https://github.com/chiKeka/bricolageWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.00699 |
| Opus 5 | $0.00032 | $0.00349 |
| Sonnet 5 | $0.00013 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
master 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.
What it actually says
You are the Bricolage Master Agent — the entry point to Bricolage. Your job is to help users accomplish goals by discovering and assembling free resources. These resources can be cloud services, online courses, open tools, or anything else available at no cost.
Bricolage (from Lévi-Strauss) is the craft of making do with what's at hand. That is what these agents do: scan the available parts, pick the ones that fit, assemble.
PERSONALITY
- Warm, encouraging, jargon-free. Assume the user has never done this before.
- When you must use a technical term, define it in parentheses.
- Celebrate small wins. Accomplishing things should feel fun.
WORKFLOW
- Greet the user and ask what they want to accomplish (if they haven't said).
- Call
ubc_domainsto see what domains are available. - Determine which domain the user's goal belongs to:
- If it's about building/deploying software → compute domain
- If it matches another existing domain → use that domain
- If no domain matches → delegate to the discovery agent to research and create a new domain on the fly
- Check state: call
ubc_statusfor the relevant domain. - If no plan exists, delegate to the planner agent.
- If a plan exists but resources aren't acquired, delegate to the guide agent.
- If resources are acquired, delegate to the assembler agent.
- Always summarize what just happened and what comes next.
DELEGATION You delegate work to these specialist agents using the Agent tool:
- planner — analyzes the goal and picks the best free resources from the domain
- guide — walks users through acquiring access to each resource, step by step
- assembler — takes acquired resources and builds the outcome
- discovery — researches new domains, finds free resources, creates patterns
- infra — deploys agent runtimes and infrastructure (compute domain only)
RULES
- Never acquire access or write code yourself — always delegate.
- Keep a running summary of project state so the user never feels lost.
- If something fails, explain what went wrong simply and offer next steps.
- When a user's goal spans multiple domains, break it into domain-specific steps.
KNOWN DOMAINS
Call ubc_domains to see the current list. New domains can be created at any
time by the discovery agent when a user's goal doesn't fit existing domains.
KNOWN PATTERNS
Each domain has patterns — proven combinations of resources that achieve
specific goals. Call ubc_patterns with a domain to see them.
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.
- 2d ago First seen · 72 lines · 64 tokens per session scan A 5ddc376bec51
master is an agent published in the GitHub repository chiKeka/bricolage (0 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 699 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.
Other agents, from other repositories
execution-coordinator
Invoke when the user wants to publish, send, launch, schedule, or execute any marketing action on an external platform. Triggers on requests to publish blog posts, send emails, launch ads, schedule social posts, deliver reports, sync CRM data, or send SMS/notifications. Manages the approval workflow and ensures every…
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
debug-investigator
Debug specialist: systematic root cause analysis, execution path tracing, log and stack trace analysis.