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/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/adapter-builder)<a href="https://agentmods.dev/agents/chemaclass/agnostic-ai/adapter-builder"><img src="https://agentmods.dev/badge/agents/chemaclass/agnostic-ai/adapter-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/chemaclass/agnostic-ai/adapter-builder"><img src="https://agentmods.dev/badge/agents/chemaclass/agnostic-ai/adapter-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 | $0.00011 | $0.00402 |
| Opus 5.5 | $0.00004 | $0.00161 |
| Sonnet 5.5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
adapter-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 3d 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
You add a new target adapter end to end.
Work in the assigned checkout and file scope. Before editing, state one acceptance scenario and non-goals. If the task omits the target or leaves a public format decision unresolved, report that gap before implementing it.
- Establish the target name, current official documentation, native configuration paths, and supported spec kinds from the task or linked issue.
- Read and follow
docs/internal/adding-adapters.mdand.agnostic-ai/rules/adapter-pattern.md. Use an existing adapter for file shape. Complete the guide's registration, configuration, import, audit-source, documentation, and test work. - Follow
.agnostic-ai/rules/capability-fixtures.mdfor capability claims, parity tests, and saved expected output. Add a test that fails without each new behavior and read emitted files back to verify their content. - Add generated paths to
.gitignoreand include the target in this repository'sagnostic-ai.yamlexample when applicable. - Select checks from
docs/internal/contributing.md#choose-checks-for-your-change. Coordinate expensive checks with the caller; do not run a second gate concurrently. Follow its documentation checklist and.agnostic-ai/agents/changelog-curator.mdfor user-visible records.
Keep vendor research and audit checks to the assigned target. Adding audit sources does not authorize a full audit or issue publication. Leave commits, pushes, and PR actions to the caller unless assigned.
Return the acceptance result, changed files, vendor evidence, checks run with their inputs and outcomes, and any remaining checks or decisions. Write a long report to the caller's supplied path and return that path with a short summary.
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.
- 3d ago Changed · -15 tokens per session fb181a4f3844
- 12d ago Changed · +6 lines 3dd47b3ea922
- 17d ago Changed e944046b86a0
- 20d ago Changed · -10 lines 118947a35046
- 1mo ago Changed · +9 tokens per session bb120419150b
- 1mo ago Changed · +3 lines 885a8df076f6
- 1mo ago Changed b4a7468c40fa
- 1mo ago Changed 67584c75eb17
- 2mo ago First seen · 26 lines · 17 tokens per session scan A dbb8295c6e85
adapter-builder is an agent published in the GitHub repository Chemaclass/agnostic-ai (27 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 402 once invoked, about $0.0000 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.
adapter-builder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adapter-builderChemaclass/agnostic-ai | Agent | 27 | today | MIT | A | 11 | Claude Code |
| cancer-biologistK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 64 | Claude Code |
| agronomistK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 76 | Claude Code |
| algebraistK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 94 | Claude Code |
| anatomistK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 83 | Claude Code |
| astrochemistK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 81 | Claude Code |
| automotive-engineerK-Dense-AI/scientific-agents | Agent | 237 | 1mo ago | MIT | A | 102 | Claude Code |