Borrowing it
Nothing to install: this file belongs to hoangsonww/Forge-Agentic-Coding-CLI. 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/hoangsonww/Forge-Agentic-Coding-CLI/master/.agents/skills/add-provider/SKILL.mdgit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-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/skills/hoangsonww/forge-agentic-coding-cli/add-provider)<a href="https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/add-provider"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/add-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/hoangsonww/forge-agentic-coding-cli/add-provider"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/add-provider.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 | $0.00037 | $0.00438 |
| Opus 5.5 | $0.00015 | $0.00175 |
| Sonnet 5.5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
add-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.
What it actually says
Copy the shape of an existing provider (src/models/ollama.ts,
src/models/openai.ts, src/models/anthropic.ts). Do not invent a new
shape.
1. src/models/<name>.ts
- Match the existing provider interface (availability probe, chat/complete, token count, streaming).
- Availability probe ≤ 1.5 seconds. Long timeouts break REPL cold-start budget.
- HTTP via
undici(already a dependency). Noaxios, nonode-fetch. - Redact credentials via
src/security/redact.tsbefore any log call. - Map transport errors to
ForgeRuntimeErrorwith the rightretryableflag and arecoveryHintwhere possible.
2. src/models/registry.ts
- Add the id to
providerEnum. - Register the class in
initProviders. - If local (runs on the user's machine), add it to
isLocalProvider.
3. src/models/local-catalog.ts
- Add model id → family classification here. Do not write ad-hoc regex in the provider for capability detection.
4. src/models/router.ts
- Verify routing reaches the new provider via standard rules. If
routing changes, update
test/unit/adapter.test.ts.
5. Unit test
Mock the transport (see test/unit/adapter.test.ts). Cover:
- availability probe success and failure,
- chat/complete happy path,
- 429 retry behaviour,
- auth failure surfaces a non-retryable structured error.
6. Docs
Update the provider table in docs/ARCHITECTURE.md §6, bump the
README "At a glance" count, and add a one-line setup note to
docs/SETUP.md.
Finish with the verify skill.
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 · 54 lines · 37 tokens per session scan A 9847d99da93a
add-provider is a skill published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (26 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 438 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 2026-08-30.
add-provider compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-providerhoangsonww/Forge-Agentic-Coding-CLI | Skill | 26 | 1mo ago | MIT | A | 37 | Claude Code, Codex |
| building-agentsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 85 | Claude Code, Codex |
| agent-evalericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 79 | Claude Code, Codex |
| code-revieweralirezarezvani/claude-code-tresor | Skill | 782 | 4mo ago | MIT | A | 54 | Claude Code |
| git-commit-helperalirezarezvani/claude-code-tresor | Skill | 782 | 4mo ago | MIT | A | 55 | Claude Code |
| test-generatoralirezarezvani/claude-code-tresor | Skill | 782 | 4mo ago | MIT | A | 55 | Claude Code |
| readme-updateralirezarezvani/claude-code-tresor | Skill | 782 | 4mo ago | MIT | A | 49 | Claude Code |