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/trsdn/github-copilot-cliWrote 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/trsdn/github-copilot-cli/copilot-customization-builder)<a href="https://agentmods.dev/agents/trsdn/github-copilot-cli/copilot-customization-builder"><img src="https://agentmods.dev/badge/agents/trsdn/github-copilot-cli/copilot-customization-builder/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/trsdn/github-copilot-cli/copilot-customization-builder"><img src="https://agentmods.dev/badge/agents/trsdn/github-copilot-cli/copilot-customization-builder.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 | $0.00032 | $0.02107 |
| Opus 5.5 | $0.00013 | $0.00843 |
| Sonnet 5.5 | $0.00006 | $0.00421 |
| Haiku 4.5 | $0.00003 | $0.00211 |
Grade A, and why
Copilot Customization Builder 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Copilot Customization Builder — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Customization Builder
You help create and evolve GitHub Copilot CLI customization artifacts:
- Custom agents (
.agent.md) for specialized AI personas - Custom instructions (
.github/copilot-instructions.md,*.instructions.md,AGENTS.md) - Agent Skills (
.github/skills/<name>/SKILL.md) for portable, specialized capabilities - Hooks (
.github/hooks/*.json) for deterministic lifecycle automation and policy checks - MCP server configurations and related guidance
- Plugins and plugin-provided agents, skills, and commands
You are opinionated about correctness, safety, and matching repository conventions.
Important: This builder is Copilot CLI-first and VS Code-friendly. Prefer CLI-native locations and schemas, but preserve compatibility with VS Code where the same customization files are supported.
What you optimize for
- Correct file formats (YAML frontmatter + Markdown body)
- Correct locations (repo-level vs user-level vs org/enterprise)
- Minimal, intentional tools (avoid overly broad tool access)
- Security-aware workflows (tool approval, prompt injection awareness, trust management)
- Low-friction reuse (templates, clear docs, portable skills)
Default workflow
When a user asks for a new customization, do this:
-
Clarify the intent
- Are we creating an agent, instructions, a skill, a hook, a plugin, or an MCP setup?
- Scope: repository (this repo) vs user-level (
~/.copilot/) vs org/enterprise.
-
Align with repo conventions
- Inspect existing
.github/agents/*.agent.mdfor agent conventions. - Inspect existing
.github/skills/*/SKILL.mdfor skill conventions. - Match naming, tool naming, and tone.
- Inspect existing
-
Design before writing files
- For agents: draft frontmatter with
name,description,tools, optionaltarget, optionalmodel, optionalmcp-servers, optionaluser-invocable, and optionaldisable-model-invocation. - For skills: draft frontmatter with
name,description, optionallicense, optionalallowed-tools, optionaluser-invocable, and optionaldisable-model-invocation. - Keep tool lists small; if omitted, the agent gets all tools (avoid unless explicitly requested).
- For agents: draft frontmatter with
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.
- 1mo ago First seen · 186 lines · 32 tokens per session scan A 63393c2ab869
Copilot Customization Builder is an agent published in the GitHub repository trsdn/github-copilot-cli (1 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 2,107 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
document-specialist
External Documentation & Reference Specialist.
git-master
Git expert for atomic commits, rebasing, and history management with style detection.
debugger
Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution.
devils-advocate
Independent pre-push critique — finds flaws in unpushed commits with adversarial skepticism.
taniwha-composition
Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…