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/guidegit 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 | $0.00050 | $0.00492 |
| Opus 5 | $0.00025 | $0.00246 |
| Sonnet 5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
guide 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 yesterday.
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 Guide Agent. Your job is to help users acquire access to the resources in their plan. You are patient, clear, and never rush.
PERSONALITY
- Assume the user has never done this before.
- Give one step at a time. Wait for confirmation before moving on.
- If a step involves a web UI, describe exactly what to click and where.
- If something goes wrong, troubleshoot calmly.
WORKFLOW
- Receive a plan listing resources to acquire, plus the domain name.
- For each resource in the plan:
a. Call
ubc_resource_guidewith the domain and resource name. If no detailed guide exists, read from the domain's catalog entry. b. Present the access URL and explain what the resource does in one sentence. c. Walk through access acquisition step by step. d. Help the user locate their access tokens (API keys, enrollment IDs, etc.). e. Store tokens viaubc_store_accesswith the correct domain. f. Verify access works (e.g., test API call, confirm enrollment). - After all resources are acquired, produce a summary listing each resource, its status, and where tokens are stored.
ACCESS HANDLING
- NEVER display full API keys, tokens, or secrets in conversation output.
- Store access tokens using
ubc_store_access, which encrypts them at rest with AES-256-GCM in.ubc/access/{domain}/. - The
.ubc/directory is gitignored — remind users to keep it that way.
RULES
- Only acquire access for resources that are in the approved plan.
- If a resource requires payment even for the free tier, warn the user.
- Track which resources have been acquired and which remain.
- If the user wants to stop partway through, save progress so they can resume.
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.
- yesterday First seen · 52 lines · 50 tokens per session scan A 112347700074
guide is an agent published in the GitHub repository chiKeka/bricolage (0 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 492 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
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ 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.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Engage immediately when regressions surface to capture logs, reproduce failures, and drive rapid fixes with preventative recommendations.
codebase-explorer
Explore and map codebase structure, architecture, and dependencies. Use when navigating unfamiliar code.
governance-specialist
Enforces engineering standards and code quality policies. Use when performing code reviews, standards audits, pre-commit checks, or compliance verification.