Borrowing it
Nothing to install: this file belongs to thomwebb/gac. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thomwebb/gac/main/.skills/adding-provider/SKILL.mdgit clone --depth 1 https://github.com/thomwebb/gacWrote 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/skills/thomwebb/gac/adding-provider)<a href="https://agentmods.dev/skills/thomwebb/gac/adding-provider"><img src="https://agentmods.dev/badge/skills/thomwebb/gac/adding-provider/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/skills/thomwebb/gac/adding-provider"><img src="https://agentmods.dev/badge/skills/thomwebb/gac/adding-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 3 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 10 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 104 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 165 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 185 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Prompt Injection · line 29 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 31 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 29 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 34 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 35 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 162 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00078 | $0.02196 |
| Opus 5.5 | $0.00031 | $0.00878 |
| Sonnet 5.5 | $0.00016 | $0.00439 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
adding-provider 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 2mo 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Provider to GAC
Overview
GAC supports 35+ providers via a registry pattern. Adding one means creating a provider class, registering it, listing it in the interactive setup CLI, advertising it in the README, and adding standardized tests. Skipping any step leaves the provider partially wired (e.g. selectable in uvx gac init but not in the registry, or callable but not advertised).
Core principle: every provider lives in five places. Touch all five.
When to Use
Use when:
- A user asks to "add X as a provider"
- You need to support a new OpenAI-compatible inference service (cheapest case — extend
OpenAICompatibleProvider) - You need to support an Anthropic-compatible or custom-protocol provider
Do NOT use for:
- Modifying behavior of an existing provider (just edit its file)
- Adding a new model to an existing provider (no code change needed; users set
GAC_MODEL)
The Five Touch Points
| # | Path | Purpose |
|---|---|---|
| 1 | src/gac/providers/<key>.py |
Provider class (NEW file) |
| 2 | src/gac/providers/__init__.py |
Import + register_provider("<key>", Cls) |
| 3 | src/gac/model_cli.py |
Add to providers list in _configure_model; add alias mapping if display name → key derivation doesn't match |
| 4 | README.md |
Add to "Supported Providers" bullet list |
| 5 | tests/providers/test_<key>.py + tests/test_ai.py + tests/test_model_cli_providers.py |
Tests (NEW + edits) |
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.
- 2mo ago First seen · 188 lines · 78 tokens per session scan A 40537b6d5f07
adding-provider is a skill published in the GitHub repository thomwebb/gac (318 stars, last pushed 18d ago), licensed MIT. It adds 78 tokens to every session and 2,196 once invoked, about $0.0003 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 2026-08-30.
adding-provider compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adding-providerthomwebb/gac | Skill | 318 | 18d ago | MIT | A | 78 | Claude Code, Codex |
| serving-llms-vllmNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 27 | Claude Code, Codex |
| open-sourcebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 137 | Claude Code |
| mem0-test-integrationmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 207 | Claude Code, Codex |
| data-leakage-detectionTencent/AI-Infra-Guard | Skill | 7.4k | yesterday | Apache-2.0 | A | 34 | Claude Code |
| bridging-presidio-and-spacymaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 154 | Claude Code |
| llmsimlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 98 | Claude Code |