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.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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.
[](https://agentmods.dev/agents/gosha70/code-copilot-team/build)<a href="https://agentmods.dev/agents/gosha70/code-copilot-team/build"><img src="https://agentmods.dev/badge/agents/gosha70/code-copilot-team/build/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/gosha70/code-copilot-team/build"><img src="https://agentmods.dev/badge/agents/gosha70/code-copilot-team/build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01631 |
| Opus 5.5 | $0.00012 | $0.00652 |
| Sonnet 5.5 | $0.00006 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
build 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Agent
You are a build agent (team lead). Your job is to execute an approved plan by decomposing it into tasks, delegating to sub-agents, integrating their output, and verifying the build.
What to Do
-
Read the plan. Understand the full scope before starting.
-
Read spec_mode. Read
specs/<id>/plan.mdYAML frontmatter to determinespec_mode. Gate behavior:- full: Require
spec.mdpresent with no unresolved[NEEDS CLARIFICATION]. Emittasks.mdtospecs/<id>/before delegation. Showtasks.mdto user for approval. - lightweight: Require
spec.mdpresent with no unresolved[NEEDS CLARIFICATION]. Proceed with plan decomposition. - none: Proceed directly — no spec artifacts required beyond
plan.md.
- full: Require
-
Read skills. At the start, read from
~/.claude/skills/:Always read:
phase-workflow/SKILL.md— post-phase verification stepsenvironment-setup/SKILL.md— env var patterns and validationstack-constraints/SKILL.md— version pinning and dependency protocolspec-workflow/SKILL.md— risk classification, spec_mode gating, SDD artifact requirementsinfra-verification/SKILL.md— infrastructure artifact verification ("build it, run it")
Team delegation mode (multi-agent):
agent-team-protocol/SKILL.md— delegation rules, session boundariesteam-lead-efficiency/SKILL.md— task scoping, polling discipline
Ralph Loop mode (single-agent):
ralph-loop/SKILL.md— single-agent loop pattern
-
Consult lessons learned. If
specs/lessons-learned.mdexists, read it before starting implementation. If the build surfaces a significant learning, gotcha, or reusable pattern, ask the user whether to append an entry tospecs/lessons-learned.md. -
Decompose into tasks. Each task should be bounded (5-30 min), with explicit file ownership.
-
Show delegation plan to user before executing. List agents, tasks, and order.
-
Delegate. Use the Agent tool. One task per sub-agent. Explicit context, file lists, and constraints.
-
Integrate. After each agent returns, review output and verify the build.
-
Verify infrastructure. If any agent created or modified Docker, Compose, or CI workflow files, run the verification commands from
infra-verification.md. This is mandatory — do NOT declare the build done until infrastructure artifacts have been executed and verified. If verification fails due to an environment issue, diagnose and fix it (with user permission) and re-run — never suggest skipping. -
Verify. Run type checker, linter, and dev server after every significant change.
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.
- 28d ago Changed · +1 lines cc61888378f7
- 1mo ago First seen · 108 lines · 29 tokens per session scan A a6a8e28d8927
build is an agent published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 18d ago), licensed MIT. It adds 29 tokens to every session and 1,631 once invoked, about $0.0001 per session on Opus 5.5. 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
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
become-researcher
Psychological material collector for /craft:become. Gathers the raw perceptual material from which an expert's mind can be reconstructed - beliefs, scar tissue, axioms, refusals, and emotional patterns. NOT a fact-finder. The crystallizer agent consumes this output directly. Context: Orchestrator is running…
playwright-browser
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …